51 models · updated 2 November 2026
Decision models with a restricted licence
Non-commercial, share-alike or inherited base terms. Listed so you find out now rather than three weeks into an integration.
laya-vision-smolvlm-256m
thaitea
SmolVLM-256M-Instruct fine-tuned to return typed decisions, 237M parameters. Licensed cc-by-nc-sa-4.0, check before commercial use.
237M · HuggingFaceTB/SmolVLM-256M-Instruct · cc-by-nc-sa-4.0
Community cardLFM2.5-350M-RLCD
notnotsamuel
A typed-decision model from notnotsamuel, 354M parameters. Licensed other, check before commercial use.
354M · other
Community cardbev-decider-0.4B
avbiswas
Qwen3-0.6B fine-tuned to return typed decisions, 478M parameters.
478M · Qwen/Qwen3-0.6B · cc-by-nc-4.0
Community cardsystem-one-qwen3.5-4b-scorer
pngwn
The largest open model in the directory and the only one aimed at a single primitive, score. Licensed cc-by-nc-4.0, which rules it out of commercial use regardless of how it benchmarks.
Qwen/Qwen3.5-4B-Base · cc-by-nc-4.0
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 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 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 cardsystem-one-qwen3.5-4b-scorer-v2b
pngwn
A LoRA adapter that turns Qwen3.5-4B-Base into a typed-decision model without shipping full weights. Licensed cc-by-nc-4.0, check before commercial use.
Qwen/Qwen3.5-4B-Base · cc-by-nc-4.0
Community cardjev-lite
vagmi
A LoRA adapter that turns gemma-4-E4B-it into a typed-decision model without shipping full weights. Licensed gemma, check before commercial use.
google/gemma-4-E4B-it · gemma
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-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 cardjevify-gemma4-e4b-GGUF
mradermacher
A GGUF build of jevify-gemma4-e4b, for running typed decisions on llama.cpp instead of a hosted API.
7.5B · kushalpatil/jevify-gemma4-e4b · gemma
Community cardlaya-cybersec
TextCortex
laya fine-tuned to return typed decisions, 322M parameters.
322M · convaiinnovations/laya · other
Community cardjevify-gemma4-26b-a4b
kushalpatil
gemma-4-26B-A4B-it fine-tuned to return typed decisions, 26B parameters.
26B · google/gemma-4-26B-A4B-it · gemma
Community cardhertz-1
telepatia-ai
parakeet-tdt-0.6b-v3 fine-tuned to return typed decisions.
nvidia/parakeet-tdt-0.6b-v3 · other
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 cardkestrel-decider-230m
Kestrelyn
LFM2.5-230M-Base fine-tuned to return typed decisions.
LiquidAI/LFM2.5-230M-Base · other
Community cardlaya-grounded
Luni
laya fine-tuned to return typed decisions, 421M parameters. Licensed cc-by-nc-4.0, check before commercial use.
421M · convaiinnovations/laya · cc-by-nc-4.0
Community cardvideo-jev
sp1d5r
Qwen3-Omni-30B-A3B-Instruct fine-tuned to return typed decisions.
Qwen/Qwen3-Omni-30B-A3B-Instruct · cc-by-nc-sa-4.0
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 cardEXAONE-4.0-1.2B-JEV-GGUF
mradermacher
A GGUF build of EXAONE-4.0-1.2B-JEV, for running typed decisions on llama.cpp instead of a hosted API.
1.3B · carrtesy/EXAONE-4.0-1.2B-JEV · other
Community cardjevify-gemma4-26b-a4b-GGUF
mradermacher
A GGUF build of jevify-gemma4-26b-a4b, for running typed decisions on llama.cpp instead of a hosted API.
25B · kushalpatil/jevify-gemma4-26b-a4b · gemma
Community cardstatim-decide-multilingual-base
Beko2210
laya-multilingual fine-tuned to return typed decisions, 322M parameters.
322M · convaiinnovations/laya-multilingual · other
Community cardsystem-one-model
stephenlb
gemma-4-12B fine-tuned to return typed decisions, 12B parameters.
12B · google/gemma-4-12B · gemma
Community cardcyber-jev
sdmlai
nano-jev fine-tuned to return typed decisions, 23M parameters.
23M · sdmlai/nano-jev · cc-by-nc-4.0
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 cardJevK5-FP8
liodon-ai
A quantised build of JevK5, for running typed decisions on a local runtime instead of a hosted API.
4.2B · alibiserikbay/JevK5 · other
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 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 cardstatim-decide-multilingual-base-safety
Beko2210
statim-decide-multilingual-base fine-tuned to return typed decisions, 3M parameters.
3M · Beko2210/statim-decide-multilingual-base · other
Community cardgemma3-270m-typed-decisions
rony
gemma-3-270m-it fine-tuned to return typed decisions, 268M parameters.
268M · google/gemma-3-270m-it · gemma
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 cardEXAONE-4.0-1.2B-JEV
carrtesy
EXAONE-4.0-1.2B fine-tuned to return typed decisions, 1.3B parameters.
1.3B · LGAI-EXAONE/EXAONE-4.0-1.2B · other
Community cardgemma-3-270m-jev-mlx
bzantium
An MLX build of gemma-3-270m-jev, for running typed decisions on Apple Silicon instead of a hosted API.
google/gemma-3-270m-it · gemma
Community cardjevify-gemma4-e4b
kushalpatil
gemma-4-E4B-it fine-tuned to return typed decisions, 7.9B parameters.
7.9B · google/gemma-4-E4B-it · gemma
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 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 cardsystem-one-270m
kaivoss
gemma-3-270m-it fine-tuned to return typed decisions, 268M parameters.
268M · unsloth/gemma-3-270m-it · gemma
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 cardsystem-one-qwen3.5-4b-scorer-ONNX
onnx-community
An ONNX build of system-one-qwen3.5-4b-scorer, for running typed decisions on ONNX Runtime instead of a hosted API.
pngwn/system-one-qwen3.5-4b-scorer · cc-by-nc-4.0
Community cardsurebranch-4b
edihasaj
decider-4b fine-tuned to return typed decisions, 4.2B parameters.
4.2B · Mapika/decider-4b · cc-by-sa-4.0
Community cardlfm2-5-350m-rlcd-coreml
FluidInference
LFM2.5-350M-RLCD fine-tuned to return typed decisions.
notnotsamuel/LFM2.5-350M-RLCD · other
Community cardstatim-decide-multilingual-base-actions
Beko2210
statim-decide-multilingual-base fine-tuned to return typed decisions, 3M parameters.
3M · Beko2210/statim-decide-multilingual-base · other
Community cardLFM2.5-350M-RLCD-FP8
liodon-ai
A quantised build of LFM2.5-350M-RLCD, for running typed decisions on a local runtime instead of a hosted API.
354M · notnotsamuel/LFM2.5-350M-RLCD · other
Community cardsystem-one-qwen3.5-4b-scorer-ONNX-etheroi
developerjeremylive
An ONNX build of Qwen3.5-4B-Base, for running typed decisions on ONNX Runtime instead of a hosted API.
Qwen/Qwen3.5-4B-Base · cc-by-nc-4.0
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 cardsystem-one-qwen3.5-4b-scorer-smoke
pngwn
Qwen3.5-4B-Base fine-tuned to return typed decisions.
Qwen/Qwen3.5-4B-Base · cc-by-nc-4.0
Community cardLFM2.5-1.2B-RLCD
goutam
LFM2.5-1.2B-Base fine-tuned to return typed decisions, 1.2B parameters.
1.2B · LiquidAI/LFM2.5-1.2B-Base · other
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.