105 models · updated 2 November 2026
Decision models beyond English
Models whose cards claim a language other than English. The community benchmark everyone reports against is English only, so none of these have a comparable public number.
laya-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 cardagent-jev
aimeigaoshou
Qwen3-0.6B fine-tuned to return typed decisions, 598M parameters.
598M · Qwen/Qwen3-0.6B · 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 cardLFM2.5-350M-RLCD
notnotsamuel
A typed-decision model from notnotsamuel, 354M parameters. Licensed other, check before commercial use.
354M · other
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 cardmodernbert-ja-310m-jev
argos1111
modernbert-ja-310m fine-tuned to return typed decisions, 315M parameters. Licensed cc-by-sa-4.0, check before commercial use.
315M · sbintuitions/modernbert-ja-310m · cc-by-sa-4.0
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 cardLFM2.5-2.6B-RLCD
monotykamary
LFM2.5-2.6B fine-tuned to return typed decisions, 2.7B parameters. Licensed other, check before commercial use.
2.7B · LiquidAI/LFM2.5-2.6B · other
Community cardraya
TextCortex
laya fine-tuned to return typed decisions, 322M parameters.
322M · convaiinnovations/laya · 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 cardara-jev-Faisal
Omartificial-Intelligence-Space
Qwen3.5-4B fine-tuned to return typed decisions, 4.7B parameters.
4.7B · Qwen/Qwen3.5-4B · cc-by-nc-4.0
Community cardserigy-jev
wendellperbar
manaca-1b-base fine-tuned to return typed decisions.
AIInstituteLNCC/manaca-1b-base · mit
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 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 cardlaya-hebrew
RoeiG
neodictabert-bilingual fine-tuned to return typed decisions, 378M parameters.
378M · dicta-il/neodictabert-bilingual · cc-by-nc-sa-4.0
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 cardlaya-pt-es-typed
telepatia-ai
laya-multilingual fine-tuned to return typed decisions, 322M parameters.
322M · convaiinnovations/laya-multilingual · apache-2.0
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 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 cardarchai-jev-zagreus-0.4b-ita
nickprock
zagreus-0.4B-ita fine-tuned to return typed decisions, 438M parameters.
438M · mii-llm/zagreus-0.4B-ita
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 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 cardLaya-Hebrew-V2.1
RoeiG
Laya-Hebrew-V2 fine-tuned to return typed decisions, 406M parameters.
406M · RoeiG/Laya-Hebrew-V2 · cc-by-nc-sa-4.0
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 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 cardlaya-cybersec
TextCortex
laya fine-tuned to return typed decisions, 322M parameters.
322M · convaiinnovations/laya · other
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 cardQwev-9B-RLCD
gyung
kev-9b fine-tuned to return typed decisions.
jaredpalmer/kev-9b · 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 cardhertz-1
telepatia-ai
parakeet-tdt-0.6b-v3 fine-tuned to return typed decisions.
nvidia/parakeet-tdt-0.6b-v3 · other
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-guard-v3.2-2b
hubin
Qwen3.5-2B fine-tuned to return typed decisions.
Qwen/Qwen3.5-2B · other
Community cardjev-ru-4b-lora-v2
nouton
A LoRA adapter that turns Qwen3.5-4B into a typed-decision model without shipping full weights.
Qwen/Qwen3.5-4B · cc-by-nc-4.0
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 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 cardLFM2.5-350M-RLCD-GGUF
NANI-Nithin
A GGUF build of LFM2.5-350M-RLCD, for running typed decisions on llama.cpp instead of a hosted API.
354M · notnotsamuel/LFM2.5-350M-RLCD · other
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 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 cardOpenThai-SystemOne-Ollama
iapp
OpenThai-SystemOne fine-tuned to return typed decisions, 752M parameters.
752M · iapp/OpenThai-SystemOne · apache-2.0
Community cardstatim-decide-multilingual-base
Beko2210
laya-multilingual fine-tuned to return typed decisions, 322M parameters.
322M · convaiinnovations/laya-multilingual · other
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 cardErabo-2B
tanakaisworking
decider-2b fine-tuned to return typed decisions, 1.9B parameters.
1.9B · Mapika/decider-2b · apache-2.0
Community cardGemma-1B-Jev-Decision-Classification-SystemOne
mondk
gemma-3-1b-pt fine-tuned to return typed decisions, 1000M parameters.
1000M · google/gemma-3-1b-pt · gemma
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 carddana-laya-0.3b-persian
amiralifirouzi
laya-multilingual fine-tuned to return typed decisions, 322M parameters.
322M · convaiinnovations/laya-multilingual · 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 cardLaya-Hebrew-V2
RoeiG
laya-hebrew fine-tuned to return typed decisions, 406M parameters.
406M · RoeiG/laya-hebrew · cc-by-nc-sa-4.0
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 cardstatim-decide-multilingual-base-pii
Beko2210
statim-decide-multilingual-base fine-tuned to return typed decisions, 3M parameters.
3M · Beko2210/statim-decide-multilingual-base · other
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 cardArbiter-4B
Goddragon
NeoHorse-Jev-4B fine-tuned to return typed decisions.
TokenRhythm/NeoHorse-Jev-4B · apache-2.0
Community cardJev-LCT-Adapters
CaoHaoWei
Jev-LCT-Adapters, an open-weight model published to return typed decisions.
apache-2.0
Community cardkodoom
Farahani
laya-multilingual fine-tuned to return typed decisions.
convaiinnovations/laya-multilingual · 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 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 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 cardara-jev-Faisal-GGUF
mradermacher
A GGUF build of ara-jev-Faisal, for running typed decisions on llama.cpp instead of a hosted API.
4.3B · Omartificial-Intelligence-Space/ara-jev-Faisal · cc-by-nc-4.0
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-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 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 cardjev-japanese-judgment
fukayatti0
LFM2.5-1.2B-JP-202606 fine-tuned to return typed decisions, 3M parameters.
3M · LiquidAI/LFM2.5-1.2B-JP-202606 · other
Community cardlaya-swedish-preference-gate
jonasaise
laya fine-tuned to return typed decisions, 322M parameters.
322M · convaiinnovations/laya · 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 cardllm-jp-4.1-33b-systemone-experimental
shunmoridev
llm-jp-4.1-33b-thinking fine-tuned to return typed decisions, 33B parameters.
33B · llm-jp/llm-jp-4.1-33b-thinking · other
Community cardModernBERT-Ja-310M-Decision-LiteRT
mlboydaisuke
A quantised build of modernbert-ja-310m-jev, for running typed decisions on a local runtime instead of a hosted API.
argos1111/modernbert-ja-310m-jev · cc-by-sa-4.0
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 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 cardDelveta-LayaChoice-v2
eric-ml-nlp
laya fine-tuned to return typed decisions.
convaiinnovations/laya
Community cardlaya-bangla
algolyzer
laya-multilingual fine-tuned to return typed decisions, 322M parameters.
322M · convaiinnovations/laya-multilingual · 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 cardxlm-roberta-systemone
itsdevice
xlm-roberta-base fine-tuned to return typed decisions, 278M parameters.
278M · FacebookAI/xlm-roberta-base · mit
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 cardstatim-decide-multilingual-base-emotion
Beko2210
statim-decide-multilingual-base fine-tuned to return typed decisions, 3M parameters.
3M · Beko2210/statim-decide-multilingual-base · other
Community cardvigil
safecircleai
A quantised build of laya-multilingual, for running typed decisions on a local runtime instead of a hosted API.
322M · convaiinnovations/laya-multilingual · other
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 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 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 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 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 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 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 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 cardlaya-multilingual-bn-ecom-voice
nafiullah
laya-multilingual fine-tuned to return typed decisions, 322M parameters.
322M · convaiinnovations/laya-multilingual · cc-by-nc-sa-4.0
Community cardLaya-Multilingual-CoreAI
mlboydaisuke
laya fine-tuned to return typed decisions.
convaiinnovations/laya · 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-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.