412 models · updated 2 November 2026
Decision models you can use commercially
Apache-2.0 and MIT only. The licence is the first thing that rules a model out of a product, and it rules more of them out than people expect.
laya
convaiinnovations
The most-liked open-weight decision model of the post-Jev wave, a 421M ModernBERT-large encoder. The base release of a three-model family.
421M · apache-2.0
Community cardJEV-27B-VL
autotrust
Qwen3.8-27B fine-tuned to return typed decisions, 28B parameters.
28B · Qwen/Qwen3.8-27B · apache-2.0
Community cardJEV-35B
autotrust
Qwen3.5-35B-A3B fine-tuned to return typed decisions, 36B parameters.
36B · Qwen/Qwen3.5-35B-A3B · apache-2.0
Community cardQwen-2.5-1B-RLCD
harshatheg
Qwen2.5-1.5B-Instruct fine-tuned to return typed decisions.
Qwen/Qwen2.5-1.5B-Instruct · apache-2.0
Community cardJEV-27B
autotrust
Qwen3.8-27B fine-tuned to return typed decisions, 27B parameters.
27B · Qwen/Qwen3.8-27B · apache-2.0
Community cardAutoTrust-JEV-27B-v1.1
autotrust
AutoTrust-JEV-27B-v1.1, an open-weight model published to return typed decisions, 27B parameters.
27B · apache-2.0
Community cardJev-Omni
akhilaaa3
gemma-4-12B-it fine-tuned to return typed decisions.
google/gemma-4-12B-it · apache-2.0
Community cardlaya-multilingual
convaiinnovations
The only multilingual decision model we have found, a 322M encoder on mmBERT. Also the one our English-only test set cannot say anything useful about.
322M · apache-2.0
Community cardlaya-typed-decisions
convaiinnovations
The Laya variant tuned on the typed-decisions benchmark, and the only open model whose card publishes head-to-head numbers against Jev. One of those numbers is the reason we started measuring.
421M · apache-2.0
Community cardlaya-mlx
aac6fef
laya fine-tuned to return typed decisions, 421M parameters.
421M · convaiinnovations/laya · apache-2.0
Community cardJEV-35B-NVFP4
autotrust
A quantised build of JEV-35B, for running typed decisions on a local runtime instead of a hosted API.
20B · autotrust/JEV-35B · apache-2.0
Community cardJEV-9B
autotrust
Qwen3.5-9B fine-tuned to return typed decisions, 9B parameters.
9B · Qwen/Qwen3.5-9B · apache-2.0
Community cardcua-s1-forms
cua-ai
A System One model narrowed to one job, filling forms. MIT licensed, and the clearest example in the directory of the interface spreading past the benchmark it was born on.
mit
Community carddecider-2b
Mapika
The most-downloaded open-weight decision model in the post-Jev wave. A Qwen3.5-2B decoder fine-tuned to emit typed decisions, and the largest member of a three-model family.
1.9B · Qwen/Qwen3.5-2B-Base · apache-2.0
Community cardembeddinggemma-2-ft-typed-decision
mrm8488
embeddinggemma-2 fine-tuned to return typed decisions, 272M parameters.
272M · google/embeddinggemma-2 · apache-2.0
Community cardopen-jev-deberta-v3-large
com-kotobalabs
A DeBERTa-v3-large encoder positioned as an open reimplementation of Jev. The highest ratio of likes to downloads in the directory, which is usually what a credible claim looks like early.
434M · microsoft/deberta-v3-large · apache-2.0
Community cardstrands-decider-2B-hobson-v19
StrandsAgents
Qwen3.5-2B-Base fine-tuned to return typed decisions.
Qwen/Qwen3.5-2B-Base · apache-2.0
Community cardJEV-CPU
Meanblock
Qwen3-0.6B fine-tuned to return typed decisions.
Qwen/Qwen3-0.6B · mit
Community cardOpen-Jev-9B
ZefanCai
Qwen3.5-9B fine-tuned to return typed decisions.
Qwen/Qwen3.5-9B · apache-2.0
Community cardlaya-coreml
FluidInference
A Core ML build of laya, for running typed decisions on on-device Apple runtimes instead of a hosted API.
convaiinnovations/laya · apache-2.0
Community cardagent-jev
aimeigaoshou
Qwen3-0.6B fine-tuned to return typed decisions, 598M parameters.
598M · Qwen/Qwen3-0.6B · apache-2.0
Community cardrlcd-modernbert-151m
heman10x
The smallest decision model we track, at 151M parameters on a GLiClass/ModernBERT encoder. If it holds accuracy, it changes what this class of model costs to run.
151M · knowledgator/gliclass-modern-base-v2.0 · apache-2.0
Community cardLaya-GGUF
ggml-org
A GGUF build of laya, for running typed decisions on llama.cpp instead of a hosted API.
421M · convaiinnovations/laya · apache-2.0
Community cardOpenThai-SystemOne
iapp
Qwen3.5-0.8B-Base fine-tuned to return typed decisions, 753M parameters.
753M · Qwen/Qwen3.5-0.8B-Base · apache-2.0
Community carddecider-2b-vision
Mapika
Qwen3.5-2B-Base fine-tuned to return typed decisions, 2.2B parameters.
2.2B · Qwen/Qwen3.5-2B-Base · apache-2.0
Community cardlaya-browser
cklxx
laya fine-tuned to return typed decisions.
convaiinnovations/laya · apache-2.0
Community cardNeoHorse-Jev-4B
TokenRhythm
NeoHorse-1-4B fine-tuned to return typed decisions.
TokenRhythm/NeoHorse-1-4B · apache-2.0
Community cardstrands-decider-2B-hobson-v21
StrandsAgents
Qwen3.5-2B-Base fine-tuned to return typed decisions.
Qwen/Qwen3.5-2B-Base · apache-2.0
Community carddecider-4b
Mapika
Qwen3.5-4B-Base fine-tuned to return typed decisions, 4.2B parameters.
4.2B · Qwen/Qwen3.5-4B-Base · apache-2.0
Community cardJev-Style-Qwen3.5-2B-Decision-GGUF
chaoliangUNSW
A GGUF build of Jev-Style-Qwen3.5-2B-Decision, for running typed decisions on llama.cpp instead of a hosted API.
1.9B · Qwen/Qwen3.5-2B-Base · apache-2.0
Community cardJevK5
alibiserikbay
Qwen3.5-4B fine-tuned to return typed decisions, 4.2B parameters.
4.2B · Qwen/Qwen3.5-4B · apache-2.0
Community cardlaya-GGUF
mys
A GGUF build of laya, for running typed decisions on llama.cpp instead of a hosted API.
convaiinnovations/laya · apache-2.0
Community cardJev-Style-0.8B-Decision-v3-GGUF
chaoliangUNSW
A GGUF build of Jev-Style-0.8B-Decision-v3, for running typed decisions on llama.cpp instead of a hosted API.
752M · chaoliangUNSW/Jev-Style-0.8B-Decision-v3 · apache-2.0
Community cardmini-Jev
samatv256
Qwen3-0.6B fine-tuned to return typed decisions.
0M · Qwen/Qwen3-0.6B · apache-2.0
Community cardmatilda-jev-v1
Maincode
Qwen3.8-27B fine-tuned to return typed decisions, 26B parameters.
26B · Qwen/Qwen3.8-27B · apache-2.0
Community cardJEV-Gemma4-26B-A4B
autotrust
gemma-4-26B-A4B-it fine-tuned to return typed decisions, 26B parameters.
26B · google/gemma-4-26B-A4B-it · apache-2.0
Community cardOpen-Jev-2B
ZefanCai
Qwen3.5-2B fine-tuned to return typed decisions.
Qwen/Qwen3.5-2B · apache-2.0
Community cardcua-s1-forms-coreml
FluidInference
A Core ML build of cua-s1-forms, for running typed decisions on on-device Apple runtimes instead of a hosted API.
cua-ai/cua-s1-forms · mit
Community cardlaya-multilingual-GGUF
mys
A GGUF build of laya-multilingual, for running typed decisions on llama.cpp instead of a hosted API.
convaiinnovations/laya-multilingual · apache-2.0
Community cardlaya-multilingual-mlx
aac6fef
laya-multilingual fine-tuned to return typed decisions, 322M parameters.
322M · convaiinnovations/laya-multilingual · apache-2.0
Community cardlaya-onnx
Mattepiu
A ONNX build of laya, for running typed decisions on runtimes without PyTorch instead of a hosted API.
convaiinnovations/laya · apache-2.0
Community cardOpen-Jev-27B-v1.1
ZefanCai
Qwen3.8-27B fine-tuned to return typed decisions.
Qwen/Qwen3.8-27B · apache-2.0
Community cardlaya-gguf
fr0stbit3
A GGUF build of laya, for running typed decisions on llama.cpp instead of a hosted API.
395M · convaiinnovations/laya · apache-2.0
Community cardpplx-decider-27B-Artemis-GGUF
turintech
A GGUF build of pplx-decider-27B-Artemis, for running typed decisions on llama.cpp instead of a hosted API.
27B · perplexity-ai/pplx-decider-v1.1-27b · apache-2.0
Community cardMiniCPM5-2B-Jev
ytbai
MiniCPM5-2B fine-tuned to return typed decisions.
openbmb/MiniCPM5-2B · apache-2.0
Community cardjev
feder-cr
jev, an open-weight model published to return typed decisions, 882M parameters.
882M · mit
Community cardJeff-1
GestaltLabs
A LoRA adapter that turns Qwen3-4B-Instruct-2507 into a typed-decision model without shipping full weights.
Qwen/Qwen3-4B-Instruct-2507 · apache-2.0
Community cardstrands-decider-2B-qwen3.5-v1-2610
StrandsAgents
Qwen3.5-2B-Base fine-tuned to return typed decisions.
Qwen/Qwen3.5-2B-Base · apache-2.0
Community cardJEV-27B-VL-GGUF
Atlas3D
A GGUF build of JEV-27B-VL, for running typed decisions on llama.cpp instead of a hosted API.
27B · autotrust/JEV-27B-VL · apache-2.0
Community cardJev-Omni-Q4_K_M-GGUF
Reza2kn
A GGUF build of Jev-Omni, for running typed decisions on llama.cpp instead of a hosted API.
12B · akhilaaa3/Jev-Omni · apache-2.0
Community cardNeoHorse-Jev-4B-GGUF
TokenRhythm
A GGUF build of NeoHorse-Jev-4B, for running typed decisions on llama.cpp instead of a hosted API.
TokenRhythm/NeoHorse-Jev-4B · apache-2.0
Community cardlaya-mind2web-browser-agent
ShaunSpark
laya fine-tuned to return typed decisions.
convaiinnovations/laya · apache-2.0
Community cardsuper-decider
Singularity-Compute
diffusiongemma-26B-A4B-it fine-tuned to return typed decisions, 14B parameters.
14B · google/diffusiongemma-26B-A4B-it · apache-2.0
Community cardlaya-multilingual-coreml-ane
aac6fef
A Core ML build of laya-multilingual, for running typed decisions on on-device Apple runtimes instead of a hosted API.
convaiinnovations/laya-multilingual · apache-2.0
Community carddecider-35b-a3b
Mapika
Qwen3.5-35B-A3B-Base fine-tuned to return typed decisions, 35B parameters.
35B · Qwen/Qwen3.5-35B-A3B-Base · apache-2.0
Community cardJev-Style-2B-Decision-v3
chaoliangUNSW
Qwen3.5-2B fine-tuned to return typed decisions, 1.9B parameters.
1.9B · Qwen/Qwen3.5-2B · apache-2.0
Community cardJev-Style-2B-Decision-v3-GGUF
chaoliangUNSW
A GGUF build of Jev-Style-2B-Decision-v3, for running typed decisions on llama.cpp instead of a hosted API.
1.9B · chaoliangUNSW/Jev-Style-2B-Decision-v3 · apache-2.0
Community carddecider-0.8b
Mapika
Qwen3.5-0.8B-Base fine-tuned to return typed decisions, 752M parameters.
752M · Qwen/Qwen3.5-0.8B-Base · apache-2.0
Community carddecider-2b-GGUF
cosetoenor
A GGUF build of decider-2b, for running typed decisions on llama.cpp instead of a hosted API.
Mapika/decider-2b · apache-2.0
Community carddecider-35b-a3b-nvfp4
Mapika
A typed-decision model from Mapika, 18B parameters.
18B · Mapika/decider-35b-a3b · apache-2.0
Community cardJev-Style-Qwen3.5-2B-Decision-v2-GGUF
chaoliangUNSW
A GGUF build of Jev-Style-Qwen3.5-2B-Decision-v2, for running typed decisions on llama.cpp instead of a hosted API.
1.9B · chaoliangUNSW/Jev-Style-Qwen3.5-2B-Decision-v2 · apache-2.0
Community cardjev-schema-scorer-deberta-v3-large
mobarmg
deberta-v3-large fine-tuned to return typed decisions, 435M parameters.
435M · microsoft/deberta-v3-large · mit
Community cardraya
TextCortex
laya fine-tuned to return typed decisions, 322M parameters.
322M · convaiinnovations/laya · apache-2.0
Community cardlaya-coreml
aac6fef
A Core ML build of laya, for running typed decisions on on-device Apple runtimes instead of a hosted API.
convaiinnovations/laya · apache-2.0
Community cardOn-Fly-Jev
Quazim0t0
On-Fly-Jev, an open-weight model published to return typed decisions.
apache-2.0
Community cardJEV-27B-VL-MLX-4bit
Bayway
An MLX build of JEV-27B-VL, for running typed decisions on Apple Silicon instead of a hosted API.
27B · autotrust/JEV-27B-VL · apache-2.0
Community cardlaya-multilingual-GGUF
Weidows
A GGUF build of laya-multilingual, for running typed decisions on llama.cpp instead of a hosted API.
307M · convaiinnovations/laya-multilingual · apache-2.0
Community cardLaya-Multilingual-LiteRT
litert-community
A quantised build of laya-multilingual, for running typed decisions on a local runtime instead of a hosted API.
convaiinnovations/laya-multilingual · apache-2.0
Community cardlaya-typed-decisions-GGUF
mys
A GGUF build of laya-typed-decisions, for running typed decisions on llama.cpp instead of a hosted API.
convaiinnovations/laya-typed-decisions · apache-2.0
Community carddecider-31b
Mapika
A quantised build of gemma-4-31B-it, for running typed decisions on a local runtime instead of a hosted API.
21B · google/gemma-4-31B-it · apache-2.0
Community cardlaya-typed-decisions-mlx
aac6fef
laya-typed-decisions fine-tuned to return typed decisions, 421M parameters.
421M · convaiinnovations/laya-typed-decisions · apache-2.0
Community cardserigy-jev
wendellperbar
manaca-1b-base fine-tuned to return typed decisions.
AIInstituteLNCC/manaca-1b-base · mit
Community cardstrands-decider-E2B-gemma4-v1-2610
StrandsAgents
gemma-4-E2B-it fine-tuned to return typed decisions.
google/gemma-4-E2B-it · apache-2.0
Community cardJevK5-GGUF
alibiserikbay
A GGUF build of JevK5, for running typed decisions on llama.cpp instead of a hosted API.
1.9B · alibiserikbay/JevK5 · apache-2.0
Community cardJEV-9B-GGUF
prithivMLmods
A GGUF build of JEV-9B, for running typed decisions on llama.cpp instead of a hosted API.
9B · autotrust/JEV-9B · apache-2.0
Community cardJev-Style-Qwen3.5-2B-Decision-MLX-bf16
chaoliangUNSW
An MLX build of Jev-Style-Qwen3.5-2B-Decision, for running typed decisions on Apple Silicon instead of a hosted API.
1.9B · Qwen/Qwen3.5-2B-Base · apache-2.0
Community cardjev-Ternary-Bonsai-2-27B-Abliterated-PTQ1_0
hotdogs
A GGUF build of Ternary-Bonsai-2-27B-Abliterated-PTQ1_0-GGUF, for running typed decisions on llama.cpp instead of a hosted API.
27B · BoldingBuilds/Ternary-Bonsai-2-27B-Abliterated-PTQ1_0-GGUF · apache-2.0
Community cardlaya-multilingual-ONNX
onnx-community
An ONNX build of laya-multilingual, for running typed decisions on ONNX Runtime instead of a hosted API.
convaiinnovations/laya-multilingual · apache-2.0
Community cardTiny-Jev
lostargon
Qwen3-0.6B fine-tuned to return typed decisions, 596M parameters.
596M · Qwen/Qwen3-0.6B · apache-2.0
Community cardqwen3-0.6b-rlcd-decision
anthonym21
Qwen3-0.6B-Base fine-tuned to return typed decisions, 596M parameters.
596M · Qwen/Qwen3-0.6B-Base · apache-2.0
Community cardrsi-jev-v6.1-vl-27b
shgao
Qwen3.8-27B fine-tuned to return typed decisions.
Qwen/Qwen3.8-27B · apache-2.0
Community cardJEV-27B-VL-NVFP4
Atlas3D
A quantised build of JEV-27B-VL, for running typed decisions on a local runtime instead of a hosted API.
28B · autotrust/JEV-27B-VL · apache-2.0
Community cardlaya-multilingual-coreml
aac6fef
A Core ML build of laya-multilingual, for running typed decisions on on-device Apple runtimes instead of a hosted API.
convaiinnovations/laya-multilingual · apache-2.0
Community cardjev-novel-2.5-0.8b-bf16
aikexue170
Qwen3.5-0.8B fine-tuned to return typed decisions, 752M parameters.
752M · Qwen/Qwen3.5-0.8B · apache-2.0
Community cardj33-jev
J33-AI
embeddinggemma-2 fine-tuned to return typed decisions, 272M parameters.
272M · google/embeddinggemma-2 · apache-2.0
Community cardlaya-onnx
receptron
An ONNX build of laya, for running typed decisions on ONNX Runtime instead of a hosted API.
convaiinnovations/laya · apache-2.0
Community cardlaya-onnx
techtheist
An ONNX build of laya, for running typed decisions on ONNX Runtime instead of a hosted API.
convaiinnovations/laya · apache-2.0
Community carddecider-4b-GGUF
Mapika
A GGUF build of decider-4b, for running typed decisions on llama.cpp instead of a hosted API.
4.2B · Mapika/decider-4b · apache-2.0
Community cardJEV-27B-GGUF
prithivMLmods
A GGUF build of JEV-27B, for running typed decisions on llama.cpp instead of a hosted API.
27B · autotrust/JEV-27B · apache-2.0
Community cardBonsai-JEV
dakebakery
Ternary-Bonsai-2-27B-gguf fine-tuned to return typed decisions, 27B parameters.
27B · prism-ml/Ternary-Bonsai-2-27B-gguf · apache-2.0
Community carddecider-12b
Mapika
gemma-4-12B-it fine-tuned to return typed decisions, 12B parameters.
12B · google/gemma-4-12B-it · apache-2.0
Community cardlaya-LiteRT
litert-community
A quantised build of laya, for running typed decisions on a local runtime instead of a hosted API.
convaiinnovations/laya · apache-2.0
Community cardwolf-defender-jev
patronus-studio
mmBERT-small fine-tuned to return typed decisions, 151M parameters.
151M · jhu-clsp/mmBERT-small · mit
Community carddecider-chat-gemma4-31b
Mapika
gemma-4-31B-it fine-tuned to return typed decisions, 31B parameters.
31B · google/gemma-4-31B-it · apache-2.0
Community cardJEV-27B-VL-FP8
Atlas3D
A quantised build of JEV-27B-VL, for running typed decisions on a local runtime instead of a hosted API.
28B · autotrust/JEV-27B-VL · apache-2.0
Community cardmJev-Qwen3-VL-4B-RLCD
SoMarkAI
Qwen3-VL-4B-Instruct fine-tuned to return typed decisions, 4.4B parameters.
4.4B · Qwen/Qwen3-VL-4B-Instruct · apache-2.0
Community cardlaya-pt-es-typed
telepatia-ai
laya-multilingual fine-tuned to return typed decisions, 322M parameters.
322M · convaiinnovations/laya-multilingual · apache-2.0
Community cardjev-vision-27b
leinenterprises
Qwen3.8-27B fine-tuned to return typed decisions.
Qwen/Qwen3.8-27B · apache-2.0
Community cardjev-berta-base-zeroshot-classifier
leobitz
deberta-v3-base fine-tuned to return typed decisions.
microsoft/deberta-v3-base · mit
Community cardQwen3-14B-RLCD-Decision-LoRA
Foodoo1
A LoRA adapter that turns Qwen3-14B into a typed-decision model without shipping full weights.
Qwen/Qwen3-14B · apache-2.0
Community cardMobiMind-Decider-7B
IPADS-SAI
A typed-decision model from IPADS-SAI, 8.3B parameters.
8.3B · apache-2.0
Community cardlaya-multilingual-onnx
mizchi
An ONNX build of laya-multilingual, for running typed decisions on ONNX Runtime instead of a hosted API.
convaiinnovations/laya-multilingual · apache-2.0
Community cardlaya-onnx-fp16
sevenreasons
A ONNX build of laya, for running typed decisions on runtimes without PyTorch instead of a hosted API.
convaiinnovations/laya · apache-2.0
Community cardlaya-ov-int8
rupeshs
A quantised build of laya, for running typed decisions on a local runtime instead of a hosted API.
convaiinnovations/laya · apache-2.0
Community cardQwen-2.5-1B-RLCD
shreyansh26
Qwen2.5-1.5B-Instruct fine-tuned to return typed decisions.
Qwen/Qwen2.5-1.5B-Instruct · apache-2.0
Community cardstrands-decider-E4B-gemma4-v1-2610
StrandsAgents
gemma-4-E4B-it fine-tuned to return typed decisions.
google/gemma-4-E4B-it · apache-2.0
Community cardJEV-27B-VL-GGUF
prithivMLmods
A GGUF build of JEV-27B-VL, for running typed decisions on llama.cpp instead of a hosted API.
27B · autotrust/JEV-27B-VL · apache-2.0
Community cardpplx-decider-v1.1-27b-GGUF
Livesport
A GGUF build of pplx-decider-v1.1-27b, for running typed decisions on llama.cpp instead of a hosted API.
26B · perplexity-ai/pplx-decider-v1.1-27b · apache-2.0
Community carddecider-2b-GGUF
Mapika
A GGUF build of decider-2b, for running typed decisions on llama.cpp instead of a hosted API.
1.9B · Mapika/decider-2b · apache-2.0
Community cardvisual-jev-4b-answer-sft
guanxuyu
Qwen3-VL-4B-Instruct fine-tuned to return typed decisions.
Qwen/Qwen3-VL-4B-Instruct · apache-2.0
Community cardJev-Omni-GGUF
ngquocvinh
A GGUF build of Jev-Omni, for running typed decisions on llama.cpp instead of a hosted API.
12B · akhilaaa3/Jev-Omni · apache-2.0
Community cardJevK5-9B
alibiserikbay
Qwen3.5-9B fine-tuned to return typed decisions, 9B parameters.
9B · Qwen/Qwen3.5-9B · apache-2.0
Community carddecider-2b-vision-GGUF
mradermacher
A GGUF build of decider-2b-vision, for running typed decisions on llama.cpp instead of a hosted API.
Mapika/decider-2b-vision · apache-2.0
Community carddecider-0.8b-GGUF
mradermacher
A GGUF build of decider-0.8b, for running typed decisions on llama.cpp instead of a hosted API.
Mapika/decider-0.8b · apache-2.0
Community cardJEV-27B-VL-MLX-8bit
nativ-community
An MLX build of JEV-27B-VL, for running typed decisions on Apple Silicon instead of a hosted API.
27B · autotrust/JEV-27B-VL · apache-2.0
Community cardlaya-gguf-persian-multilingual-decision
fibonacciai
A GGUF build of laya, for running typed decisions on llama.cpp instead of a hosted API.
323M · convaiinnovations/laya · apache-2.0
Community cardLaya-English-LiteRT
litert-community
A quantised build of laya, for running typed decisions on a local runtime instead of a hosted API.
convaiinnovations/laya · apache-2.0
Community carddecider-2b-vision-GGUF
mindchain
A GGUF build of decider-2b-vision, for running typed decisions on llama.cpp instead of a hosted API.
1.9B · Mapika/decider-2b-vision · apache-2.0
Community cardembeddinggemma-2-ft-typed-decision-GGUF
cstr
A GGUF build of embeddinggemma-2-ft-typed-decision, for running typed decisions on llama.cpp instead of a hosted API.
272M · mrm8488/embeddinggemma-2-ft-typed-decision · apache-2.0
Community cardjev-9b-coreml
FluidInference
A Core ML build of JEV-9B, for running typed decisions on on-device Apple runtimes instead of a hosted API.
autotrust/JEV-9B · apache-2.0
Community cardMatilda-Jev-v1.5
Maincode
Qwen3.8-27B fine-tuned to return typed decisions, 26B parameters.
26B · Qwen/Qwen3.8-27B · apache-2.0
Community cardlaya-code
tindang
laya fine-tuned to return typed decisions, 421M parameters.
421M · convaiinnovations/laya · apache-2.0
Community cardjev-novel-3-27b-fp8
aikexue170
Qwen3.8-27B fine-tuned to return typed decisions, 27B parameters.
27B · Qwen/Qwen3.8-27B · apache-2.0
Community cardturnike-jev-4b
berkay123001
Qwen3.5-4B fine-tuned to return typed decisions.
Qwen/Qwen3.5-4B · apache-2.0
Community cardjev-spatial
Fr0zencr4nE
Molmo2-ER fine-tuned to return typed decisions.
allenai/Molmo2-ER · apache-2.0
Community cardlaya-multilingual-onnx-int4
androidli
An ONNX build of laya, for running typed decisions on ONNX Runtime instead of a hosted API.
convaiinnovations/laya · apache-2.0
Community cardlaya-vision
savita10
laya fine-tuned to return typed decisions.
convaiinnovations/laya · apache-2.0
Community cardod1-typed-decisions
mvbalaji
Qwen3.5-4B fine-tuned to return typed decisions.
Qwen/Qwen3.5-4B · apache-2.0
Community cardstrands-decider-12B-gemma4-v1-2610
StrandsAgents
gemma-4-12B-it fine-tuned to return typed decisions.
google/gemma-4-12B-it · apache-2.0
Community cardstrands-decider-26B-A4B-gemma4-v1-2610
StrandsAgents
gemma-4-26B-A4B-it fine-tuned to return typed decisions.
google/gemma-4-26B-A4B-it · apache-2.0
Community cardtyped-decisions-minilm-l6-specialist
adaptive-classifier
typed-decisions-minilm-l6-specialist, an open-weight model published to return typed decisions.
apache-2.0
Community cardGemma-4-12B-Unified-System-One-GGUF
mradermacher
A GGUF build of Gemma-4-12B-Unified-System-One, for running typed decisions on llama.cpp instead of a hosted API.
12B · knowlet/Gemma-4-12B-Unified-System-One · apache-2.0
Community carddecider-4b-GGUF
mradermacher
A GGUF build of decider-4b, for running typed decisions on llama.cpp instead of a hosted API.
4.2B · Mapika/decider-4b · apache-2.0
Community cardJev-Omni-MLX-4bit
Ruiruiz30
An MLX build of Jev-Omni, for running typed decisions on Apple Silicon instead of a hosted API.
12B · akhilaaa3/Jev-Omni · apache-2.0
Community cardlaya-MLX-8bit
cavi-ai
An MLX build of laya, for running typed decisions on Apple Silicon instead of a hosted API.
421M · convaiinnovations/laya · apache-2.0
Community cardtasksource-decider-nano
tasksource
ettin-reranker-150m-v1 fine-tuned to return typed decisions, 149M parameters.
149M · cross-encoder/ettin-reranker-150m-v1 · apache-2.0
Community carddecider-4b-v2-GGUF
mindchain
A GGUF build of decider-4b-v2, for running typed decisions on llama.cpp instead of a hosted API.
4.2B · Mapika/decider-4b · apache-2.0
Community cardministral3-3b-reasoning-typed-decisions
rony
Ministral-3-3B-Reasoning-2512 fine-tuned to return typed decisions, 3.4B parameters.
3.4B · mistralai/Ministral-3-3B-Reasoning-2512 · apache-2.0
Community cardJevEmbed-Qwen3-Embedding-0.6B
HIT-TMG
Qwen3-Embedding-0.6B fine-tuned to return typed decisions, 596M parameters.
596M · Qwen/Qwen3-Embedding-0.6B · apache-2.0
Community cardlaya-onnx
inferenceprince
An ONNX build of laya, for running typed decisions on ONNX Runtime instead of a hosted API.
convaiinnovations/laya · apache-2.0
Community cardjev-control-core
abhishek085
A GGUF build of Qwen3.5-0.8B-Base, for running typed decisions on llama.cpp instead of a hosted API.
752M · Qwen/Qwen3.5-0.8B-Base · apache-2.0
Community cardnano-jev
sdmlai
MiniLM-L12-H384-uncased fine-tuned to return typed decisions, 33M parameters.
33M · microsoft/MiniLM-L12-H384-uncased · mit
Community cardJevEmbed-Qwen3-Embedding-4B
HIT-TMG
Qwen3-Embedding-4B fine-tuned to return typed decisions, 4B parameters.
4B · Qwen/Qwen3-Embedding-4B · apache-2.0
Community cardlaya-typed-decisions-onnx
ti3x-m
An ONNX build of laya-typed-decisions, for running typed decisions on ONNX Runtime instead of a hosted API.
convaiinnovations/laya-typed-decisions · apache-2.0
Community carddecider-2b-dwq-4bit
midium-ai
decider-2b fine-tuned to return typed decisions, 1.9B parameters.
1.9B · Mapika/decider-2b · apache-2.0
Community cardlaya-neutron-gguf
wigcheng5566
A GGUF build of laya, for running typed decisions on llama.cpp instead of a hosted API.
395M · convaiinnovations/laya · apache-2.0
Community cardJevEmbed-KaLM-Embedding-V2.5
HIT-TMG
KaLM-embedding-multilingual-mini-instruct-v2.5 fine-tuned to return typed decisions, 494M parameters.
494M · KaLM-Embedding/KaLM-embedding-multilingual-mini-instruct-v2.5 · apache-2.0
Community carddecider-4b-dwq-4bit
midium-ai
An MLX build of decider-4b, for running typed decisions on Apple Silicon instead of a hosted API.
4.2B · Mapika/decider-4b · apache-2.0
Community cardopen-jev-laya-multilingual-onnx
killkli
open-jev-laya-multilingual-onnx, an open-weight model published to return typed decisions.
apache-2.0
Community cardlaya-v
henilchopada
laya fine-tuned to return typed decisions, 752M parameters.
752M · convaiinnovations/laya · apache-2.0
Community cardmatilda-jev-fp4
Maincode
matilda-jev-fp4, an open-weight model published to return typed decisions, 15B parameters.
15B · apache-2.0
Community cardMatilda-Jev-v1-FP4
Maincode
Matilda-Jev-v1-FP4, an open-weight model published to return typed decisions, 15B parameters.
15B · apache-2.0
Community cardVTX-JEV-1
VTXAI
VTX-JEV-1, an open-weight model published to return typed decisions, 7M parameters.
7M · apache-2.0
Community cardvisual-jev-budget20-qwen35-0.8b-lora
harshnandwana
A LoRA adapter that turns Qwen3.5-0.8B-Base into a typed-decision model without shipping full weights.
Qwen/Qwen3.5-0.8B-Base · apache-2.0
Community cardrsi-jev-v6.0-vl-4b
shgao
Qwen3.5-4B-Base fine-tuned to return typed decisions.
Qwen/Qwen3.5-4B-Base · apache-2.0
Community cardOmniMed-Jev-4B
xmutly
medgemma-1.5-4b-it fine-tuned to return typed decisions.
google/medgemma-1.5-4b-it · apache-2.0
Community cardqwen3-0.6b-rlcd
thefloydd
Qwen3-0.6B-Base fine-tuned to return typed decisions.
Qwen/Qwen3-0.6B-Base · apache-2.0
Community carddecider-4b-fp8
llmtech
A quantised build of decider-4b, for running typed decisions on a local runtime instead of a hosted API.
4.2B · Mapika/decider-4b · apache-2.0
Community cardjev-novel-2.5-4b-bf16
aikexue170
Qwen3.5-4B fine-tuned to return typed decisions, 4.2B parameters.
4.2B · Qwen/Qwen3.5-4B · apache-2.0
Community cardphishing_spam_jev_like_classifier
akumar0205
phishing_spam_jev_like_classifier, an open-weight model published to return typed decisions, 67M parameters.
67M · apache-2.0
Community cardQwev-9B-RLCD
gyung
kev-9b fine-tuned to return typed decisions.
jaredpalmer/kev-9b · apache-2.0
Community cards1-jev-cvltist
AEECollier
Qwen3.5-4B fine-tuned to return typed decisions.
Qwen/Qwen3.5-4B · apache-2.0
Community cardlaya-burmese-sib200
aungthuhein-dev
laya fine-tuned to return typed decisions, 322M parameters.
322M · convaiinnovations/laya · apache-2.0
Community carddecider-12b-NPU-LPBQ-X-Elite
tielmane
An ONNX build of decider-12b, for running typed decisions on ONNX Runtime instead of a hosted API.
Mapika/decider-12b · apache-2.0
Community cardlaya-onnx
desplega
An ONNX build of laya, for running typed decisions on ONNX Runtime instead of a hosted API.
convaiinnovations/laya · apache-2.0
Community cardgyra
RomanRG008
laya fine-tuned to return typed decisions, 421M parameters.
421M · convaiinnovations/laya · apache-2.0
Community cardHydraQwen3.5-0.8B-Jev
athrael-soju
Qwen3.5-0.8B fine-tuned to return typed decisions.
Qwen/Qwen3.5-0.8B · apache-2.0
Community cardJev-Style-0.8B-Decision-v3-MLX
chaoliangUNSW
An MLX build of Jev-Style-0.8B-Decision-v3, for running typed decisions on Apple Silicon instead of a hosted API.
chaoliangUNSW/Jev-Style-0.8B-Decision-v3 · apache-2.0
Community cardlaya-ko
2nugu
laya fine-tuned to return typed decisions, 322M parameters.
322M · convaiinnovations/laya · apache-2.0
Community cardlaya-multilingual-FP8
Weidows
A quantised build of laya-multilingual, for running typed decisions on a local runtime instead of a hosted API.
convaiinnovations/laya-multilingual · apache-2.0
Community cardlaya-onnx-q8
nvkudva
An ONNX build of laya, for running typed decisions on ONNX Runtime instead of a hosted API.
convaiinnovations/laya · apache-2.0
Community cardlaya-typed-decisions-ov-int8
rupeshs
A quantised build of laya-typed-decisions, for running typed decisions on a local runtime instead of a hosted API.
convaiinnovations/laya-typed-decisions · apache-2.0
Community cardlaya-web-q8
nvkudva
An ONNX build of laya, for running typed decisions on ONNX Runtime instead of a hosted API.
convaiinnovations/laya · apache-2.0
Community cardlaya-onnx
mariojcr
An ONNX build of laya, for running typed decisions on ONNX Runtime instead of a hosted API.
convaiinnovations/laya · apache-2.0
Community cardrecmeets-laya-words
somniusx
laya fine-tuned to return typed decisions.
convaiinnovations/laya · apache-2.0
Community cardlaya-multilingual-onnx
soyelmismo
An ONNX build of laya-multilingual, for running typed decisions on ONNX Runtime instead of a hosted API.
convaiinnovations/laya-multilingual · apache-2.0
Community carddepguard-jev-style-1.5b
JackKozmo29
Qwen2.5-1.5B-Instruct fine-tuned to return typed decisions, 1.5B parameters.
1.5B · Qwen/Qwen2.5-1.5B-Instruct · apache-2.0
Community cardmailguard-jev-style-1.5b
JackKozmo29
Qwen2.5-1.5B-Instruct fine-tuned to return typed decisions, 1.5B parameters.
1.5B · Qwen/Qwen2.5-1.5B-Instruct · apache-2.0
Community cardsevclassifier-jev-style-1.5b
JackKozmo29
Qwen2.5-1.5B-Instruct fine-tuned to return typed decisions, 1.5B parameters.
1.5B · Qwen/Qwen2.5-1.5B-Instruct · apache-2.0
Community cardcodeguard-jev-style-1.5b
JackKozmo29
Qwen2.5-1.5B-Instruct fine-tuned to return typed decisions, 1.5B parameters.
1.5B · Qwen/Qwen2.5-1.5B-Instruct · apache-2.0
Community carddecider-35b-a3b-GGUF
mradermacher
A GGUF build of decider-35b-a3b, for running typed decisions on llama.cpp instead of a hosted API.
35B · Mapika/decider-35b-a3b · apache-2.0
Community cardJEV-27B-VL-Uncensored-GGUF
mradermacher
A GGUF build of JEV-27B-VL-Uncensored, for running typed decisions on llama.cpp instead of a hosted API.
27B · SargeDev/JEV-27B-VL-Uncensored · apache-2.0
Community cardJev-alpha-26B-A4B
chenz53
gemma-4-26B-A4B-it fine-tuned to return typed decisions, 26B parameters.
26B · google/gemma-4-26B-A4B-it · apache-2.0
Community cardJEV-27B-VL-GGUF
PALLER-NOVUS
A GGUF build of JEV-27B-VL, for running typed decisions on llama.cpp instead of a hosted API.
27B · autotrust/JEV-27B-VL · apache-2.0
Community cardlaya-multilingual-F16-GGUF
meshllm
A GGUF build of laya-multilingual, for running typed decisions on llama.cpp instead of a hosted API.
322M · convaiinnovations/laya-multilingual · apache-2.0
Community cardJev-Style-2B-Decision-v3-MLX
chaoliangUNSW
An MLX build of Jev-Style-2B-Decision-v3, for running typed decisions on Apple Silicon instead of a hosted API.
chaoliangUNSW/Jev-Style-2B-Decision-v3 · apache-2.0
Community cardlaya-multilingual-gguf
fr0stbit3
A GGUF build of laya-multilingual, for running typed decisions on llama.cpp instead of a hosted API.
307M · convaiinnovations/laya-multilingual · apache-2.0
Community cardJevK5-2B
alibiserikbay
Qwen3.5-2B fine-tuned to return typed decisions, 1.9B parameters.
1.9B · Qwen/Qwen3.5-2B · apache-2.0
Community cardJev_Qwen3.8-27B-GGUF
ramgpt
A GGUF build of Jev_Qwen3.8-27B, for running typed decisions on llama.cpp instead of a hosted API.
27B · SargeDev/Jev_Qwen3.8-27B · apache-2.0
Community cardopen-jev-deberta-v3-large-ONNX
onnx-community
An ONNX build of open-jev-deberta-v3-large, for running typed decisions on ONNX Runtime instead of a hosted API.
com-kotobalabs/open-jev-deberta-v3-large · apache-2.0
Community cardJEV-9B-MLX-NVFP4
nativ-community
An MLX build of JEV-9B, for running typed decisions on Apple Silicon instead of a hosted API.
9B · autotrust/JEV-9B · apache-2.0
Community cardOpenThai-SystemOne-GGUF
iapp
A GGUF build of OpenThai-SystemOne, for running typed decisions on llama.cpp instead of a hosted API.
752M · iapp/OpenThai-SystemOne · apache-2.0
Community cardJEV-27B-VL-MLX-MXFP4
nativ-community
An MLX build of JEV-27B-VL, for running typed decisions on Apple Silicon instead of a hosted API.
27B · autotrust/JEV-27B-VL · apache-2.0
Community cardOpenThai-SystemOne-Ollama
iapp
OpenThai-SystemOne fine-tuned to return typed decisions, 752M parameters.
752M · iapp/OpenThai-SystemOne · apache-2.0
Community cardJev-Style-2B-Decision-v3-GGUF
mradermacher
A GGUF build of Jev-Style-2B-Decision-v3, for running typed decisions on llama.cpp instead of a hosted API.
1.9B · chaoliangUNSW/Jev-Style-2B-Decision-v3 · apache-2.0
Community cardjev-decisions-v1-model
GhostScientist
Qwen3.5-0.8B fine-tuned to return typed decisions, 752M parameters.
752M · Qwen/Qwen3.5-0.8B · apache-2.0
Community cardxDecision
mccoysc
laya-multilingual fine-tuned to return typed decisions.
convaiinnovations/laya-multilingual · apache-2.0
Community cardlaya-gguf
zerodegress
A GGUF build of laya, for running typed decisions on llama.cpp instead of a hosted API.
421M · convaiinnovations/laya · apache-2.0
Community cardJevK5-Lite
alibiserikbay
deberta-v3-large fine-tuned to return typed decisions, 434M parameters.
434M · microsoft/deberta-v3-large · apache-2.0
Community cardlaya-v796
Falconsai
laya fine-tuned to return typed decisions, 421M parameters.
421M · convaiinnovations/laya · apache-2.0
Community cardlaya-onnx-int8
inferenceprince
An ONNX build of laya, for running typed decisions on ONNX Runtime instead of a hosted API.
convaiinnovations/laya · apache-2.0
Community cardOpen-Decision-DeBERTa-v3-Large-LiteRT
litert-community
A quantised build of open-jev-deberta-v3-large, for running typed decisions on a local runtime instead of a hosted API.
com-kotobalabs/open-jev-deberta-v3-large · apache-2.0
Community cardJevForge-0.8B
AndeyTait
Qwen3.5-0.8B fine-tuned to return typed decisions.
Qwen/Qwen3.5-0.8B · apache-2.0
Community cardlaya-mm-guard-v3-gguf
OidoStudio
A GGUF build of laya-multilingual, for running typed decisions on llama.cpp instead of a hosted API.
307M · convaiinnovations/laya-multilingual · apache-2.0
Community cardJev_Qwen3.8-27B-NVFP4-FP8
SargeDev
A quantised build of Jev_Qwen3.8-27B, for running typed decisions on a local runtime instead of a hosted API.
21B · SargeDev/Jev_Qwen3.8-27B · apache-2.0
Community cardErabo-2B
tanakaisworking
decider-2b fine-tuned to return typed decisions, 1.9B parameters.
1.9B · Mapika/decider-2b · apache-2.0
Community cardJev_Qwen3.8-27B
SargeDev
Huihui-Qwen3.8-27B-abliterated fine-tuned to return typed decisions, 27B parameters.
27B · huihui-ai/Huihui-Qwen3.8-27B-abliterated · apache-2.0
Community cardJevAny-27B-SFT
tianxinwei
Qwen3.8-27B fine-tuned to return typed decisions.
Qwen/Qwen3.8-27B · apache-2.0
Community cardOOMU-SystemOne-0.6B-GGUF
oomu
OOMU-SystemOne-0.6B-GGUF, an open-weight model published to return typed decisions, 596M parameters.
596M · apache-2.0
Community carddecider-2b-coherent
Mapika
decider-2b fine-tuned to return typed decisions.
Mapika/decider-2b · apache-2.0
Community cardgemma-e2b-rlcd
larkooo
A MLX build of gemma-4-E2B-it, for running typed decisions on Apple Silicon instead of a hosted API.
5.1B · google/gemma-4-E2B-it · apache-2.0
Community carddecider-4b-nvfp4
llmtech
A quantised build of decider-4b, for running typed decisions on a local runtime instead of a hosted API.
2.4B · Mapika/decider-4b · apache-2.0
Community cardJEV-27B-VL-exl3-4bpw
jyohukuchan
JEV-27B-VL fine-tuned to return typed decisions, 8.5B parameters.
8.5B · autotrust/JEV-27B-VL · apache-2.0
Community cardJEV-27B-VL-AWQ-INT4-W4A8
aioutfitters
A quantised build of JEV-27B-VL, for running typed decisions on a local runtime instead of a hosted API.
27B · autotrust/JEV-27B-VL · apache-2.0
Community cardlaya-chess
datafreak
laya fine-tuned to return typed decisions, 421M parameters.
421M · convaiinnovations/laya · apache-2.0
Community carddecider-0.8b-fp8
llmtech
A quantised build of decider-0.8b, for running typed decisions on a local runtime instead of a hosted API.
752M · Mapika/decider-0.8b · apache-2.0
Community carddana-laya-0.3b-persian
amiralifirouzi
laya-multilingual fine-tuned to return typed decisions, 322M parameters.
322M · convaiinnovations/laya-multilingual · apache-2.0
Community cardelythros-decider-0.6b
Elythros
Qwen3-0.6B fine-tuned to return typed decisions, 596M parameters.
596M · Qwen/Qwen3-0.6B · apache-2.0
Community cardgan8-vs-jev
DKNTZMN
gan8-vs-jev, an open-weight model published to return typed decisions.
apache-2.0
Community cardlaya-coreml-adaptive-fp16
aac6fef
A Core ML build of laya, for running typed decisions on on-device Apple runtimes instead of a hosted API.
convaiinnovations/laya · apache-2.0
Community cardJev-LCT-Qwen2.5-1.5B
CaoHaoWei
Jev-LCT-Qwen2.5-1.5B, an open-weight model published to return typed decisions, 1.5B parameters.
1.5B · apache-2.0
Community carddecider-2b-fp8
llmtech
A quantised build of decider-2b, for running typed decisions on a local runtime instead of a hosted API.
1.9B · Mapika/decider-2b · apache-2.0
Community cardlocal-typed-decisions
bssgoat
A GGUF build of Qwen3-4B, for running typed decisions on llama.cpp instead of a hosted API.
4B · Qwen/Qwen3-4B · apache-2.0
Community carddecider-2b-a11y-crawler-lora
johannhartmann
A LoRA adapter that turns decider-2b into a typed-decision model without shipping full weights.
Mapika/decider-2b · apache-2.0
Community cardjev-decider-qwen3-4b
mogita
Qwen3-4B fine-tuned to return typed decisions.
Qwen/Qwen3-4B · apache-2.0
Community cardjev-my-bro-th1200
JonusNattapong
laya-multilingual fine-tuned to return typed decisions, 322M parameters.
322M · convaiinnovations/laya-multilingual · apache-2.0
Community cardMiya-0.2
snowman6
laya-multilingual fine-tuned to return typed decisions.
convaiinnovations/laya-multilingual · apache-2.0
Community cardlaya-typed-decisions-421m-coreml-ane
NMTZ
A Core ML build of laya-typed-decisions, for running typed decisions on on-device Apple runtimes instead of a hosted API.
convaiinnovations/laya-typed-decisions · apache-2.0
Community cardlaya-en-fp32-swev
danielamitay
A Core ML build of laya, for running typed decisions on on-device Apple runtimes instead of a hosted API.
convaiinnovations/laya · apache-2.0
Community cardlaya-typed-decisions
akshatbindal
laya-typed-decisions, an open-weight model published to return typed decisions, 421M parameters.
421M · apache-2.0
Community cardAlpha
SofiTesfay2010
laya fine-tuned to return typed decisions, 423M parameters.
423M · convaiinnovations/laya · apache-2.0
Community cardArbiter-4B
Goddragon
NeoHorse-Jev-4B fine-tuned to return typed decisions.
TokenRhythm/NeoHorse-Jev-4B · apache-2.0
Community cardJEV-9B
ArthurZ
JEV-9B fine-tuned to return typed decisions.
autotrust/JEV-9B · apache-2.0
Community cardbialy
paintedwolfcode
laya-multilingual fine-tuned to return typed decisions.
convaiinnovations/laya-multilingual · apache-2.0
Community cardbielik-minitron-jev-v0.1
wwydmanski
Bielik-Minitron-7B-v3.0-Instruct fine-tuned to return typed decisions.
speakleash/Bielik-Minitron-7B-v3.0-Instruct · apache-2.0
Community cardbuild-jev-from-scratch
azharmo
build-jev-from-scratch, an open-weight model published to return typed decisions.
mit
Community cardByrne-Jev-79M
Quazim0t0
Byrne-Jev-79M, an open-weight model published to return typed decisions.
apache-2.0
Community cardcertus-jev-like-v0007
ait-hf
Qwen2.5-1.5B-Instruct fine-tuned to return typed decisions.
Qwen/Qwen2.5-1.5B-Instruct · apache-2.0
Community cardcode-oracle-laya-421m
wxsys
laya fine-tuned to return typed decisions, 421M parameters.
421M · convaiinnovations/laya · apache-2.0
Community cardcua-s1-forms-onnx
yasserrmd
An ONNX build of cua-s1-forms, for running typed decisions on ONNX Runtime instead of a hosted API.
cua-ai/cua-s1-forms · mit
Community cardcut-laya-onnx
harshpreet931
An ONNX build of laya, for running typed decisions on ONNX Runtime instead of a hosted API.
convaiinnovations/laya · apache-2.0
Community carddaylens-laya-onnx
aaronalexS
An ONNX build of laya, for running typed decisions on ONNX Runtime instead of a hosted API.
convaiinnovations/laya · apache-2.0
Community cardembeddinggemma-2-typed-decision-decisionjs
Jacqkues
embeddinggemma-2-ft-typed-decision fine-tuned to return typed decisions.
mrm8488/embeddinggemma-2-ft-typed-decision · apache-2.0
Community cardjev-d-0.4b-onnx
MissingPackage
laya-typed-decisions fine-tuned to return typed decisions.
convaiinnovations/laya-typed-decisions · apache-2.0
Community cardJev-LCT-Adapters
CaoHaoWei
Jev-LCT-Adapters, an open-weight model published to return typed decisions.
apache-2.0
Community cardjev-qwen35-08b
guoan1
Qwen3.5-0.8B-Base fine-tuned to return typed decisions.
Qwen/Qwen3.5-0.8B-Base · apache-2.0
Community cardkodoom
Farahani
laya-multilingual fine-tuned to return typed decisions.
convaiinnovations/laya-multilingual · apache-2.0
Community cardlaya-banking77-v1
Cahol
laya fine-tuned to return typed decisions.
convaiinnovations/laya · apache-2.0
Community cardlaya-command-head
leehack
laya fine-tuned to return typed decisions.
convaiinnovations/laya · apache-2.0
Community cardlaya-multilingual-onnx-int8
Sharjeelbaig
An ONNX build of laya-multilingual, for running typed decisions on ONNX Runtime instead of a hosted API.
convaiinnovations/laya-multilingual · apache-2.0
Community cardlaya-news-decisions
InfinimindCreations
laya fine-tuned to return typed decisions, 322M parameters.
322M · convaiinnovations/laya · apache-2.0
Community cardlaya-snake-mlx
madhavbiplov
An MLX build of laya-multilingual-mlx, for running typed decisions on Apple Silicon instead of a hosted API.
322M · aac6fef/laya-multilingual-mlx · apache-2.0
Community cardlayaForWeb
VishalMysore
An ONNX build of laya, for running typed decisions on ONNX Runtime instead of a hosted API.
convaiinnovations/laya · apache-2.0
Community cardlayaForWebTrained
VishalMysore
An ONNX build of laya-typed-decisions, for running typed decisions on ONNX Runtime instead of a hosted API.
convaiinnovations/laya-typed-decisions · apache-2.0
Community cardod1-nano-v2-typed-decisions
mvbalaji
Qwen3.5-0.8B fine-tuned to return typed decisions.
Qwen/Qwen3.5-0.8B · apache-2.0
Community cardlaya-onnx
rarha
An ONNX build of laya, for running typed decisions on ONNX Runtime instead of a hosted API.
convaiinnovations/laya · apache-2.0
Community cardrubert-tiny-turbo-typed-decisions-ru
yyhlm
rubert-tiny-turbo fine-tuned to return typed decisions, 32M parameters.
32M · sergeyzh/rubert-tiny-turbo · apache-2.0
Community cardlaya-browser
wuyuanpei
laya fine-tuned to return typed decisions.
convaiinnovations/laya · apache-2.0
Community cardJEV-35B-GGUF
mradermacher
A GGUF build of JEV-35B, for running typed decisions on llama.cpp instead of a hosted API.
36B · autotrust/JEV-35B · apache-2.0
Community cardJEV-9B-GGUF
mradermacher
A GGUF build of JEV-9B, for running typed decisions on llama.cpp instead of a hosted API.
9B · autotrust/JEV-9B · apache-2.0
Community cardSakura-Humanlike-Chat-2.0-JEV-AutoRound-GGUF
webmp3
A GGUF build of JEV-27B, for running typed decisions on llama.cpp instead of a hosted API.
27B · autotrust/JEV-27B · apache-2.0
Community cardGemma-4-12B-Unified-System-One-GGUF
knowlet
A GGUF build of Gemma-4-12B-Unified-System-One, for running typed decisions on llama.cpp instead of a hosted API.
12B · knowlet/Gemma-4-12B-Unified-System-One · apache-2.0
Community cardJEV-27B-Uncensored-GGUF
mradermacher
A GGUF build of JEV-27B-Uncensored, for running typed decisions on llama.cpp instead of a hosted API.
27B · SargeDev/JEV-27B-Uncensored · apache-2.0
Community cardworkmagic-jev-churn-distill-qwen3-8b-v1
workmagicio
Qwen3-8B fine-tuned to return typed decisions, 8.2B parameters.
8.2B · Qwen/Qwen3-8B · apache-2.0
Community cardjev-novel-2.5-4b-GGUF
aikexue170
A GGUF build of jev-novel-2.5-4b-bf16, for running typed decisions on llama.cpp instead of a hosted API.
4.2B · aikexue170/jev-novel-2.5-4b-bf16 · apache-2.0
Community cardjev-vlm-4b-lite-gguf
sidman007
A GGUF build of jev-vlm-4b-lite, for running typed decisions on llama.cpp instead of a hosted API.
4.2B · Qwen/Qwen3.5-4B-Base · apache-2.0
Community cardlaya-multilingual-GGUF
andreilungeanu
A GGUF build of laya-multilingual, for running typed decisions on llama.cpp instead of a hosted API.
322M · convaiinnovations/laya-multilingual · apache-2.0
Community cardedceleste-decider-0.8b-GGUF
mradermacher
A GGUF build of edceleste-decider-0.8b, for running typed decisions on llama.cpp instead of a hosted API.
752M · IqSantiagow/edceleste-decider-0.8b · apache-2.0
Community cardmetask-jev-rain-31B-trained
MeTask-Rain
gemma-4-31B-it fine-tuned to return typed decisions, 33B parameters.
33B · google/gemma-4-31B-it · apache-2.0
Community cardSolar-JEV-Gemma-embed-2-GGUF
SargeDev
A GGUF build of Solar-JEV-Gemma-embed-2, for running typed decisions on llama.cpp instead of a hosted API.
271M · google/embeddinggemma-2 · apache-2.0
Community cardoss-jev-qwen05-decision
gyanbhambhani
Qwen2.5-0.5B-Instruct fine-tuned to return typed decisions, 494M parameters.
494M · Qwen/Qwen2.5-0.5B-Instruct · apache-2.0
Community cardstrands-decider-2B-hobson-v19-GGUF
fabricant451
A GGUF build of strands-decider-2B-hobson-v19, for running typed decisions on llama.cpp instead of a hosted API.
1.9B · StrandsAgents/strands-decider-2B-hobson-v19 · apache-2.0
Community cardoss-jev-qwen05-decision-noul-bal
gyanbhambhani
oss-jev-qwen05-decision-noul-v2 fine-tuned to return typed decisions, 494M parameters.
494M · gyanbhambhani/oss-jev-qwen05-decision-noul-v2 · apache-2.0
Community cardstrands-decider-2B-hobson-v19-ONNX
onnx-community
An ONNX build of strands-decider-2B-hobson-v19, for running typed decisions on ONNX Runtime instead of a hosted API.
StrandsAgents/strands-decider-2B-hobson-v19 · apache-2.0
Community cardJev-Style-Qwen3.5-2B-Decision-v2-MLX-bf16
chaoliangUNSW
An MLX build of Jev-Style-Qwen3.5-2B-Decision-v2, for running typed decisions on Apple Silicon instead of a hosted API.
1.9B · chaoliangUNSW/Jev-Style-Qwen3.5-2B-Decision-v2 · apache-2.0
Community cardlaya-ONNX
onnx-community
An ONNX build of laya, for running typed decisions on ONNX Runtime instead of a hosted API.
convaiinnovations/laya · apache-2.0
Community cardNeoHorse-Jev-4B-GGUF
DreamBlooms
A GGUF build of NeoHorse-Jev-4B, for running typed decisions on llama.cpp instead of a hosted API.
4.2B · TokenRhythm/NeoHorse-Jev-4B · apache-2.0
Community cardoss-jev-qwen05-decision-noul-v2
gyanbhambhani
oss-jev-qwen05-decision-noul-bin fine-tuned to return typed decisions, 494M parameters.
494M · gyanbhambhani/oss-jev-qwen05-decision-noul-bin · apache-2.0
Community cardCoral-decider-4b-GGUF
mradermacher
A GGUF build of Coral-decider-4b, for running typed decisions on llama.cpp instead of a hosted API.
4.2B · OceanLabs/Coral-4b · apache-2.0
Community cardelythros-decider-0.6b-GGUF
mradermacher
A GGUF build of elythros-decider-0.6b, for running typed decisions on llama.cpp instead of a hosted API.
596M · Elythros/elythros-decider-0.6b · apache-2.0
Community cardoss-jev-qwen05-decision-1k
gyanbhambhani
Qwen2.5-0.5B-Instruct fine-tuned to return typed decisions, 494M parameters.
494M · Qwen/Qwen2.5-0.5B-Instruct · apache-2.0
Community cardmetask-jev-rain-12B-trained
MeTask-Rain
gemma-4-12B-it-qat-q4_0-unquantized fine-tuned to return typed decisions, 12B parameters.
12B · google/gemma-4-12B-it-qat-q4_0-unquantized · apache-2.0
Community cardsystemone-lite-0.5b
dwidlee
A 0.5B decision model on Qwen2.5, the only entry here built on a previous-generation base. Real downloads, zero likes.
494M · Qwen/Qwen2.5-0.5B-Instruct · apache-2.0
Community cardlaya-modernbert-decision-90pct
ameerhmz5
laya fine-tuned to return typed decisions, 421M parameters.
421M · convaiinnovations/laya · apache-2.0
Community cardarchai-jev-games-1.5b-v2
nickprock
archai-jev-qwen-1.5b fine-tuned to return typed decisions, 1.5B parameters.
1.5B · nickprock/archai-jev-qwen-1.5b · apache-2.0
Community cardaimtas-laya-multilingual-GGUF
letrthang
A GGUF build of laya-multilingual, for running typed decisions on llama.cpp instead of a hosted API.
322M · convaiinnovations/laya-multilingual · apache-2.0
Community cardjev-student-4b-yizao
vincentzhou
A GGUF build of Qwen3.5-4B-Base, for running typed decisions on llama.cpp instead of a hosted API.
4.2B · Qwen/Qwen3.5-4B-Base · apache-2.0
Community cardJev-Style-Qwen3.5-2B-Decision-v2
chaoliangUNSW
Qwen3.5-2B-Base fine-tuned to return typed decisions, 1.9B parameters.
1.9B · Qwen/Qwen3.5-2B-Base · apache-2.0
Community cardlaya-typed-decisions-ONNX
onnx-community
An ONNX build of laya-typed-decisions, for running typed decisions on ONNX Runtime instead of a hosted API.
convaiinnovations/laya-typed-decisions · apache-2.0
Community cardlaya-typed-decisions-gguf
fr0stbit3
A GGUF build of laya-typed-decisions, for running typed decisions on llama.cpp instead of a hosted API.
395M · convaiinnovations/laya-typed-decisions · apache-2.0
Community cardGemma-4-12B-Unified-System-One-MLX-8bit
knowlet
An MLX build of Gemma-4-12B-Unified-System-One, for running typed decisions on Apple Silicon instead of a hosted API.
12B · knowlet/Gemma-4-12B-Unified-System-One · apache-2.0
Community carddecider-2b-GGUF
DreamBlooms
A GGUF build of decider-2b, for running typed decisions on llama.cpp instead of a hosted API.
1.9B · Mapika/decider-2b · apache-2.0
Community cardJEV-9B-MLX-8bit
nativ-community
An MLX build of JEV-9B, for running typed decisions on Apple Silicon instead of a hosted API.
9B · autotrust/JEV-9B · apache-2.0
Community carddecider-0.8b-GGUF
seongukjeong
A GGUF build of decider-0.8b, for running typed decisions on llama.cpp instead of a hosted API.
752M · Mapika/decider-0.8b · apache-2.0
Community cardlaya-multilingual-GGUF
russian-oracle
A GGUF build of laya-multilingual, for running typed decisions on llama.cpp instead of a hosted API.
322M · convaiinnovations/laya-multilingual · apache-2.0
Community carddecider-0.8b-Q8
ma77145
A GGUF build of decider-0.8b, for running typed decisions on llama.cpp instead of a hosted API.
752M · Mapika/decider-0.8b · apache-2.0
Community cardlaya-multilingual-onnx
ti3x-m
An ONNX build of laya-multilingual, for running typed decisions on ONNX Runtime instead of a hosted API.
convaiinnovations/laya-multilingual · apache-2.0
Community cardlaya-onnx
ti3x-m
An ONNX build of laya, for running typed decisions on ONNX Runtime instead of a hosted API.
convaiinnovations/laya · apache-2.0
Community cardMobiMind-Decider-7B-GGUF
mradermacher
A GGUF build of MobiMind-Decider-7B, for running typed decisions on llama.cpp instead of a hosted API.
IPADS-SAI/MobiMind-Decider-7B · apache-2.0
Community cardTiny-Jev-1.7B
lostargon
Qwen3-1.7B fine-tuned to return typed decisions, 1.7B parameters.
1.7B · Qwen/Qwen3-1.7B · apache-2.0
Community cardJevK5-Lite-onnx
maxious
An ONNX build of JevK5-Lite, for running typed decisions on ONNX Runtime instead of a hosted API.
alibiserikbay/JevK5-Lite · apache-2.0
Community cardjev-novel-2.5-0.8b-GGUF
aikexue170
A GGUF build of jev-novel-2.5-0.8b-bf16, for running typed decisions on llama.cpp instead of a hosted API.
752M · aikexue170/jev-novel-2.5-0.8b-bf16 · apache-2.0
Community carddecider-2b-GGUF
Jeetu456
A GGUF build of decider-2b, for running typed decisions on llama.cpp instead of a hosted API.
1.9B · Jeetu456/decider-2b · apache-2.0
Community carddecider-0.8b-GGUF
DreamBlooms
A GGUF build of decider-0.8b, for running typed decisions on llama.cpp instead of a hosted API.
752M · Mapika/decider-0.8b · apache-2.0
Community cardlaya-finetuned-rlcd-GGUF
Snugasabug
A GGUF build of laya, for running typed decisions on llama.cpp instead of a hosted API.
322M · convaiinnovations/laya · apache-2.0
Community cardJevK5-chat-mlx-16bit
SirSahOl
An MLX build of JevK5, for running typed decisions on Apple Silicon instead of a hosted API.
4.2B · alibiserikbay/JevK5 · apache-2.0
Community cardJEV-27B-VL-MLX-NVFP4
nativ-community
An MLX build of JEV-27B-VL, for running typed decisions on Apple Silicon instead of a hosted API.
27B · autotrust/JEV-27B-VL · apache-2.0
Community cardJev_Qwen3.8-27B-EXL3-4.0bpw
ramgpt
Jev_Qwen3.8-27B fine-tuned to return typed decisions, 7.9B parameters.
7.9B · SargeDev/Jev_Qwen3.8-27B · apache-2.0
Community cardlaya-GGUF
SandLogicTechnologies
A GGUF build of laya, for running typed decisions on llama.cpp instead of a hosted API.
421M · convaiinnovations/laya · apache-2.0
Community cardembeddinggemma-2-multimodal-typed-decision
Danny-Dasilva
embeddinggemma-2 fine-tuned to return typed decisions.
google/embeddinggemma-2 · apache-2.0
Community cardlaya
nativ-community
laya fine-tuned to return typed decisions, 421M parameters.
421M · convaiinnovations/laya · apache-2.0
Community cardjevk5-0.2-mlx-4bit
Algorythm-Canada
An MLX build of JevK5, for running typed decisions on Apple Silicon instead of a hosted API.
4.2B · alibiserikbay/JevK5 · apache-2.0
Community cardMacJev-322M-4K-Laya-GGUF
chaoliangUNSW
A GGUF build of MacJev-322M-4K-Laya, for running typed decisions on llama.cpp instead of a hosted API.
307M · chaoliangUNSW/MacJev-322M-4K-Laya · apache-2.0
Community carddecider-0.8b-GGUF
ardana-ai
A GGUF build of decider-0.8b, for running typed decisions on llama.cpp instead of a hosted API.
752M · Mapika/decider-0.8b · apache-2.0
Community cardpplx-decider-v1.1-27b
ArthurZ
pplx-decider-v1.1-27b fine-tuned to return typed decisions, 1M parameters.
1M · perplexity-ai/pplx-decider-v1.1-27b · apache-2.0
Community cardsystem-one-minicpm5-2b-q8
mpuig
An MLX build of system-one-minicpm5-2b, for running typed decisions on Apple Silicon instead of a hosted API.
2.5B · openbmb/MiniCPM5-2B-Base · mit
Community carddecider-0.8b-GGUF
mindchain
A GGUF build of decider-0.8b, for running typed decisions on llama.cpp instead of a hosted API.
752M · Mapika/decider-0.8b · apache-2.0
Community cardjevk5-0.2-mlx-8bit
Algorythm-Canada
An MLX build of JevK5, for running typed decisions on Apple Silicon instead of a hosted API.
4.2B · alibiserikbay/JevK5 · apache-2.0
Community cardpplx-decider-v1-27b
ArthurZ
pplx-decider-v1-27b fine-tuned to return typed decisions, 1M parameters.
1M · perplexity-ai/pplx-decider-v1-27b · apache-2.0
Community carddecider-chat-qwen3.6-27b
Mapika
Qwen3.6-27B fine-tuned to return typed decisions, 28B parameters.
28B · Qwen/Qwen3.6-27B · apache-2.0
Community cardlaya-swedish-preference-gate
jonasaise
laya fine-tuned to return typed decisions, 322M parameters.
322M · convaiinnovations/laya · apache-2.0
Community cardQwen3.5-4B-typed-decisions-merged
wozniakos10
Qwen3.5-4B fine-tuned to return typed decisions, 4.7B parameters.
4.7B · unsloth/Qwen3.5-4B · apache-2.0
Community cardJEV-27B-VL-GPTQ-Int4-asym
darioooooo0o
A quantised build of JEV-27B-VL, for running typed decisions on a local runtime instead of a hosted API.
28B · autotrust/JEV-27B-VL · apache-2.0
Community cardjev-9b-coreai-w8
silv4souz4
JEV-9B fine-tuned to return typed decisions.
autotrust/JEV-9B · apache-2.0
Community cardjev-qwen3.5-4b-legal-lora
Nebulaw1
A LoRA adapter that turns Qwen3.5-4B-Base into a typed-decision model without shipping full weights.
Qwen/Qwen3.5-4B-Base · apache-2.0
Community cardvoice-decisions-laya-v4
Borcherding
laya fine-tuned to return typed decisions, 421M parameters.
421M · convaiinnovations/laya · apache-2.0
Community carddecider-2b
nativ-community
decider-2b fine-tuned to return typed decisions, 1.9B parameters.
1.9B · Mapika/decider-2b · apache-2.0
Community cardNeoHorse-Jev-4B-TmuxPocket-MLX-oQ4
groxaxo
An MLX build of NeoHorse-Jev-4B-TmuxPocket-MLX5, for running typed decisions on Apple Silicon instead of a hosted API.
4.2B · groxaxo/NeoHorse-Jev-4B-TmuxPocket-MLX5 · apache-2.0
Community cardQwen3.5-4B-typed-decisions
wozniakos10
Qwen3.5-4B fine-tuned to return typed decisions.
unsloth/Qwen3.5-4B · apache-2.0
Community cardJevK5-chat-mlx-8bit
SirSahOl
An MLX build of JevK5, for running typed decisions on Apple Silicon instead of a hosted API.
4.2B · alibiserikbay/JevK5 · apache-2.0
Community cardQwen3.5-0.8B-Typed-Decisions
SnowGemma
Qwen3.5-0.8B fine-tuned to return typed decisions, 873M parameters.
873M · Qwen/Qwen3.5-0.8B · apache-2.0
Community cardsn92-df-dm9b
whynotBeTop
JevK5-9B fine-tuned to return typed decisions, 9B parameters.
9B · alibiserikbay/JevK5-9B · apache-2.0
Community carddecider-4b-W8A16
rovangju
decider-4b fine-tuned to return typed decisions, 4.2B parameters.
4.2B · Mapika/decider-4b · apache-2.0
Community cardsarashina2.2-vision-3b-mmproj-jev-f16
argos1111
A GGUF build of sarashina2.2-vision-3b, for running typed decisions on llama.cpp instead of a hosted API.
446M · sbintuitions/sarashina2.2-vision-3b · mit
Community cardjeb-typed-decisions
IJyad
jeb fine-tuned to return typed decisions, 178M parameters.
178M · IJyad/jeb · apache-2.0
Community carddecider-2b
Jeetu456
Qwen3.5-2B-Base fine-tuned to return typed decisions, 1.9B parameters.
1.9B · Qwen/Qwen3.5-2B-Base · apache-2.0
Community carddecision-head-qwen3.5-4b-rlcd-32k
AstroHan
Qwen3.5-4B fine-tuned to return typed decisions.
Qwen/Qwen3.5-4B · apache-2.0
Community cardsystem-one-mini
DavidHatley
distilbert-base-uncased fine-tuned to return typed decisions, 69M parameters.
69M · distilbert/distilbert-base-uncased · apache-2.0
Community cardlaya-typed-decisions-ONNX
m1rhan
An ONNX build of laya-typed-decisions, for running typed decisions on ONNX Runtime instead of a hosted API.
convaiinnovations/laya-typed-decisions · apache-2.0
Community cardvera-deberta-v3-large
NovusEdge
open-jev-deberta-v3-large fine-tuned to return typed decisions, 435M parameters.
435M · com-kotobalabs/open-jev-deberta-v3-large · apache-2.0
Community cardopenjev-rlcd-qwen3-4b-v1
dknguyen2304
Qwen3-4B fine-tuned to return typed decisions, 4B parameters.
4B · Qwen/Qwen3-4B · apache-2.0
Community cardsystem-one-gold
shreyanbr
deberta-v3-xsmall-zeroshot-v1.1-all-33 fine-tuned to return typed decisions, 71M parameters.
71M · MoritzLaurer/deberta-v3-xsmall-zeroshot-v1.1-all-33 · apache-2.0
Community cardlaya-multilingual-coreml-adaptive-fp16
aac6fef
A Core ML build of laya-multilingual, for running typed decisions on on-device Apple runtimes instead of a hosted API.
convaiinnovations/laya-multilingual · apache-2.0
Community cardNeoHorse-Jev-4B-TmuxPocket-MLX5
groxaxo
An MLX build of NeoHorse-Jev-4B, for running typed decisions on Apple Silicon instead of a hosted API.
4.2B · TokenRhythm/NeoHorse-Jev-4B · apache-2.0
Community cardlaya-typed-decisions-ce-1024
minhleduc
laya fine-tuned to return typed decisions, 421M parameters.
421M · convaiinnovations/laya · apache-2.0
Community carddecider-2b-homelab-router
daviestechlabs
decider-2b fine-tuned to return typed decisions, 1.9B parameters.
1.9B · Mapika/decider-2b · apache-2.0
Community cardJEV-Qwen3.5-9B-Base-NVFP4
WIlfLin
A quantised build of Qwen3.5-9B-NVFP4, for running typed decisions on a local runtime instead of a hosted API.
9.4B · ig1/Qwen3.5-9B-NVFP4 · apache-2.0
Community cardlaya-typed-decisions-coreml
aac6fef
A Core ML build of laya-typed-decisions, for running typed decisions on on-device Apple runtimes instead of a hosted API.
convaiinnovations/laya-typed-decisions · apache-2.0
Community cardlaya-typed-decisions-coreml-adaptive-fp16
aac6fef
A Core ML build of laya-typed-decisions, for running typed decisions on on-device Apple runtimes instead of a hosted API.
convaiinnovations/laya-typed-decisions · apache-2.0
Community cardocf-typed-decisions-mbert-base
MSGEncrypted
ModernBERT-base fine-tuned to return typed decisions.
answerdotai/ModernBERT-base · apache-2.0
Community cardlaya-bangla
algolyzer
laya-multilingual fine-tuned to return typed decisions, 322M parameters.
322M · convaiinnovations/laya-multilingual · apache-2.0
Community cardraz-systemone-nli-base
RazvanManolache
nli-deberta-v3-base fine-tuned to return typed decisions, 184M parameters.
184M · cross-encoder/nli-deberta-v3-base · mit
Community cardsystem-one-zeroshot
shreyanbr
deberta-v3-xsmall-zeroshot-v1.1-all-33 fine-tuned to return typed decisions, 71M parameters.
71M · MoritzLaurer/deberta-v3-xsmall-zeroshot-v1.1-all-33 · apache-2.0
Community carddecider-q2b-1.1b
gabrielfior
Qwen3.5-2B-Base fine-tuned to return typed decisions.
Qwen/Qwen3.5-2B-Base · apache-2.0
Community cardOpenThai-SystemOne-MLX-mxfp4
iapp
An MLX build of OpenThai-SystemOne, for running typed decisions on Apple Silicon instead of a hosted API.
752M · iapp/OpenThai-SystemOne · apache-2.0
Community cardlaya-coreml-adaptive-fp32
aac6fef
A Core ML build of laya, for running typed decisions on on-device Apple runtimes instead of a hosted API.
convaiinnovations/laya · apache-2.0
Community cardxlm-roberta-systemone
itsdevice
xlm-roberta-base fine-tuned to return typed decisions, 278M parameters.
278M · FacebookAI/xlm-roberta-base · mit
Community cardqwen3.5-9b-jev-data-mix-v2
jsaurabh
Qwen3.5-9B fine-tuned to return typed decisions.
Qwen/Qwen3.5-9B · apache-2.0
Community cardraz-systemone-nli-xsmall-openjev
RazvanManolache
nli-deberta-v3-xsmall fine-tuned to return typed decisions, 71M parameters.
71M · cross-encoder/nli-deberta-v3-xsmall · mit
Community cardGemma-4-12B-Unified-System-One-NVFP4
knowlet
A quantised build of Gemma-4-12B-Unified-System-One, for running typed decisions on a local runtime instead of a hosted API.
7.4B · knowlet/Gemma-4-12B-Unified-System-One · apache-2.0
Community carddecider-0.8b-lora-onnx
Jotapostre
An ONNX build of decider-0.8b, for running typed decisions on ONNX Runtime instead of a hosted API.
Mapika/decider-0.8b · apache-2.0
Community cardOpenThai-SystemOne-MLX-bf16
iapp
An MLX build of OpenThai-SystemOne, for running typed decisions on Apple Silicon instead of a hosted API.
752M · iapp/OpenThai-SystemOne · apache-2.0
Community cardsystem-one-distilled
shreyanbr
deberta-v3-xsmall-zeroshot-v1.1-all-33 fine-tuned to return typed decisions, 71M parameters.
71M · MoritzLaurer/deberta-v3-xsmall-zeroshot-v1.1-all-33 · apache-2.0
Community cardstrands-decider-2b-web
RabiatS
An ONNX build of strands-decider-2B-hobson-v19, for running typed decisions on ONNX Runtime instead of a hosted API.
StrandsAgents/strands-decider-2B-hobson-v19 · apache-2.0
Community cardjev-typed-decisions-causal-0.6b
abidlabs
Qwen3-0.6B-Base fine-tuned to return typed decisions.
Qwen/Qwen3-0.6B-Base · apache-2.0
Community cardsn92-df-v9
Andrew93110
JevK5-9B fine-tuned to return typed decisions, 9B parameters.
9B · alibiserikbay/JevK5-9B · apache-2.0
Community carddecider-4b-AWQ-ASYM-W4A16
Ar4ikov
A quantised build of decider-4b, for running typed decisions on a local runtime instead of a hosted API.
4.2B · Mapika/decider-4b · apache-2.0
Community cardlaya-multilingual-coreml-adaptive-fp32
aac6fef
A Core ML build of laya-multilingual, for running typed decisions on on-device Apple runtimes instead of a hosted API.
convaiinnovations/laya-multilingual · apache-2.0
Community cardlaya-typed-decisions-coreml-adaptive-fp32
aac6fef
A Core ML build of laya-typed-decisions, for running typed decisions on on-device Apple runtimes instead of a hosted API.
convaiinnovations/laya-typed-decisions · apache-2.0
Community cardlaya-english-coreml
FluidInference
A Core ML build of laya, for running typed decisions on on-device Apple runtimes instead of a hosted API.
convaiinnovations/laya · apache-2.0
Community cardlaya-homelab-router
daviestechlabs
laya-typed-decisions fine-tuned to return typed decisions, 421M parameters.
421M · convaiinnovations/laya-typed-decisions · apache-2.0
Community cardmetask-jev-4b-policy-mix
Raymond1122
Qwen3.5-4B fine-tuned to return typed decisions, 4.5B parameters.
4.5B · Qwen/Qwen3.5-4B · apache-2.0
Community cardplek-1
Drenel
A typed-decision model from Drenel, 783M parameters.
783M · apache-2.0
Community cardverdict-coreml
FluidInference
rlcd-modernbert-151m fine-tuned to return typed decisions.
heman10x/rlcd-modernbert-151m · apache-2.0
Community cardgemma-4-E4B-it-unsloth-bnb-4bit_qlora_typed-decisions-de
johannhartmann
A LoRA adapter that turns gemma-4-E4B-it into a typed-decision model without shipping full weights.
8B · google/gemma-4-E4B-it · apache-2.0
Community cardOpenThai-SystemOne-bnb-4bit
iapp
OpenThai-SystemOne fine-tuned to return typed decisions, 753M parameters.
753M · iapp/OpenThai-SystemOne · apache-2.0
Community carddecider-4b-W4A16
rovangju
decider-4b fine-tuned to return typed decisions, 4.2B parameters.
4.2B · Mapika/decider-4b · apache-2.0
Community cardOpenThai-SystemOne-MLX-8bit
iapp
An MLX build of OpenThai-SystemOne, for running typed decisions on Apple Silicon instead of a hosted API.
752M · iapp/OpenThai-SystemOne · apache-2.0
Community cardzyot-decider-12b-adapter
hiteshluke
gemma-4-12b-it fine-tuned to return typed decisions.
google/gemma-4-12b-it · apache-2.0
Community cardJEV-Qwen3.5-0.8B-Base
WIlfLin
Qwen3.5-0.8B fine-tuned to return typed decisions, 873M parameters.
873M · Qwen/Qwen3.5-0.8B · apache-2.0
Community cardbert4jev
ukung
deberta-v3-large fine-tuned to return typed decisions, 434M parameters.
434M · microsoft/deberta-v3-large · apache-2.0
Community cardlaya-bangla-lora
algolyzer
A LoRA adapter that turns laya-multilingual into a typed-decision model without shipping full weights.
322M · convaiinnovations/laya-multilingual · apache-2.0
Community cardverdict-laya
ashiksharon005
laya fine-tuned to return typed decisions, 421M parameters.
421M · convaiinnovations/laya · apache-2.0
Community cardjev-gemma-4-E2B-it-choice-64
ohtaman
An ONNX build of gemma-4-E2B-it, for running typed decisions on ONNX Runtime instead of a hosted API.
google/gemma-4-E2B-it · apache-2.0
Community cardraz-systemone-nli-xsmall
RazvanManolache
nli-deberta-v3-xsmall fine-tuned to return typed decisions, 71M parameters.
71M · cross-encoder/nli-deberta-v3-xsmall · mit
Community cardOpenThai-SystemOne-MLX-nvfp4
iapp
An MLX build of OpenThai-SystemOne, for running typed decisions on Apple Silicon instead of a hosted API.
752M · iapp/OpenThai-SystemOne · apache-2.0
Community cardOpenThai-SystemOne-W8A8-INT8
iapp
A quantised build of OpenThai-SystemOne, for running typed decisions on a local runtime instead of a hosted API.
753M · iapp/OpenThai-SystemOne · apache-2.0
Community cardJEV-27B-VL-merged
inference-sh
JEV-27B-VL fine-tuned to return typed decisions, 28B parameters.
28B · autotrust/JEV-27B-VL · apache-2.0
Community cardOpenThai-SystemOne-FP8-Dynamic
iapp
A quantised build of OpenThai-SystemOne, for running typed decisions on a local runtime instead of a hosted API.
753M · iapp/OpenThai-SystemOne · apache-2.0
Community cardOpenThai-SystemOne-NVFP4A16
iapp
OpenThai-SystemOne fine-tuned to return typed decisions, 753M parameters.
753M · iapp/OpenThai-SystemOne · apache-2.0
Community cardturkic-relevance-laya-multilingual
mutkuoz
laya-multilingual fine-tuned to return typed decisions, 307M parameters.
307M · convaiinnovations/laya-multilingual · apache-2.0
Community cardlaya-doom-v3
azalio
laya fine-tuned to return typed decisions, 421M parameters.
421M · convaiinnovations/laya · apache-2.0
Community cardOpenThai-SystemOne-MLX-4bit
iapp
An MLX build of OpenThai-SystemOne, for running typed decisions on Apple Silicon instead of a hosted API.
752M · iapp/OpenThai-SystemOne · apache-2.0
Community cardlaya-pt-es-nli
telepatia-ai
laya-multilingual fine-tuned to return typed decisions, 322M parameters.
322M · convaiinnovations/laya-multilingual · apache-2.0
Community cardsn92-df-v8
Andrew93110
JevK5-9B fine-tuned to return typed decisions, 9B parameters.
9B · alibiserikbay/JevK5-9B · apache-2.0
Community cardbulwark
Abhi268170
laya fine-tuned to return typed decisions, 421M parameters.
421M · convaiinnovations/laya · apache-2.0
Community cardlocal-system-one-student
Mannedood
ModernBERT-base fine-tuned to return typed decisions, 149M parameters.
149M · answerdotai/ModernBERT-base · mit
Community cardOpenThai-SystemOne-W4A16-GPTQ
iapp
A quantised build of OpenThai-SystemOne, for running typed decisions on a local runtime instead of a hosted API.
753M · iapp/OpenThai-SystemOne · apache-2.0
Community carddecider-2b-toolcall-guard-lora
johannhartmann
A LoRA adapter that turns decider-2b into a typed-decision model without shipping full weights.
Mapika/decider-2b · apache-2.0
Community cardlaya-sentiment-multilingual
Ramg77
laya-multilingual fine-tuned to return typed decisions, 322M parameters.
322M · convaiinnovations/laya-multilingual · apache-2.0
Community cardOpenThai-SystemOne-bnb-8bit
iapp
OpenThai-SystemOne fine-tuned to return typed decisions, 753M parameters.
753M · iapp/OpenThai-SystemOne · apache-2.0
Community cardjev-qwen3.5-0.8b-legal-lora
Nebulaw1
A LoRA adapter that turns Qwen3.5-0.8B-Base into a typed-decision model without shipping full weights.
Qwen/Qwen3.5-0.8B-Base · apache-2.0
Community cardOpenThai-SystemOne-NVFP4
iapp
OpenThai-SystemOne fine-tuned to return typed decisions, 753M parameters.
753M · iapp/OpenThai-SystemOne · apache-2.0
Community cardcua-s1-forge-rlcd
NewSonnet
cua-s1-forge-rlcd, an open-weight model published to return typed decisions.
1M · mit
Community cardcua-s1-forge-rlcd-v3
NewSonnet
cua-s1-forge-rlcd-v3, an open-weight model published to return typed decisions.
1M · mit
Community cardLaya-Multilingual-CoreAI
mlboydaisuke
laya fine-tuned to return typed decisions.
convaiinnovations/laya · apache-2.0
Community cardlaya-multilingual-coreml-ane-w8
aac6fef
A Core ML build of laya-multilingual, for running typed decisions on on-device Apple runtimes instead of a hosted API.
convaiinnovations/laya-multilingual · apache-2.0
Community cardjev-my-bro-th960
JonusNattapong
laya-multilingual fine-tuned to return typed decisions, 322M parameters.
322M · convaiinnovations/laya-multilingual · apache-2.0
Community cardlaya-multilingual-coreml-snake
aac6fef
A Core ML build of laya-multilingual, for running typed decisions on on-device Apple runtimes instead of a hosted API.
convaiinnovations/laya-multilingual · apache-2.0
Community cardjev-playground-rlcd
soyrsoyr
deberta-v3-large-zeroshot-v2.0 fine-tuned to return typed decisions.
MoritzLaurer/deberta-v3-large-zeroshot-v2.0 · mit
Community cardlaya-multitask-intents
sallout
laya-multilingual fine-tuned to return typed decisions, 322M parameters.
322M · convaiinnovations/laya-multilingual · apache-2.0
Community cardlaya-sentiment-multilingual-coreml
Ramg77
A Core ML build of laya-sentiment-multilingual, for running typed decisions on on-device Apple runtimes instead of a hosted API.
Ramg77/laya-sentiment-multilingual · apache-2.0
Find out what your data actually supports
We turn your historical decisions into a frozen test set, then tell you which model, which threshold, and how much of it you can safely automate.