60 models · checked 20 September 2026

The decision model directory

Every model we can verify exists, with its base, its licence, and a straight answer about whether anyone has measured it. One of them has been. We say so on every card.

How to read this

Decision models went from one product to a whole shelf in about five days. Jev shipped on 15 September 2026; every open-weight model below was published within the week. Nothing that recent has been checked by anyone outside the people who trained it, which is the entire reason this directory grades evidence instead of ranking models.

Benchmarked means we ran it ourselves on a frozen test split and published the numbers with confidence intervals. Community means the facts below come from a public model card and we have measured nothing. There is no middle grade, and we would rather leave a field blank than fill it from a press release.

Open weights, not yet benchmarked

Every open-weight model we could verify, including the quantised builds and adapters that other directories drop. Ordered by how much attention each one is getting, which is the only signal available until we have run them. It is not a ranking of quality.

Community card

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 card

Qwen-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 card

cua-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 card

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 card

decider-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 card

laya-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 card

open-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 card

LFM2.5-350M-RLCD

notnotsamuel

A typed-decision model from notnotsamuel, 354M parameters. Licensed other, check before commercial use.

354M · other

Community card

rlcd-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 card

modernbert-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 card

JEV-CPU

Meanblock

Qwen3-0.6B fine-tuned to return typed decisions.

Qwen/Qwen3-0.6B · mit

Community card

laya-mlx

aac6fef

laya fine-tuned to return typed decisions, 421M parameters.

421M · convaiinnovations/laya · apache-2.0

Community card

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 card

system-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 card

decider-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 card

laya-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 card

Jeff-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 card

LFM2.5-2.6B-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 card

jev-schema-scorer-deberta-v3-large

mobarmg

deberta-v3-large fine-tuned to return typed decisions, 435M parameters.

435M · microsoft/deberta-v3-large · mit

Community card

OpenThai-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 card

system-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 card

MobiMind-Decider-7B

IPADS-SAI

A typed-decision model from IPADS-SAI, 8.3B parameters.

8.3B · apache-2.0

Community card

laya-multilingual-mlx

aac6fef

laya-multilingual fine-tuned to return typed decisions, 322M parameters.

322M · convaiinnovations/laya-multilingual · apache-2.0

Community card

Qwen-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 card

decider-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 card

laya-mind2web-browser-agent

ShaunSpark

laya fine-tuned to return typed decisions.

convaiinnovations/laya · apache-2.0

Community card

decider-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 card

qwen3-0.6b-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 card

jev-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 card

laya-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 card

laya-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 card

laya-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 card

laya-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 card

decider-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 card

decider-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 card

gemma-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 card

Qwen3-14B-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 card

laya-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 card

laya-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 card

laya-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 card

qwen3-0.6b-rlcd

thefloydd

Qwen3-0.6B-Base fine-tuned to return typed decisions.

Qwen/Qwen3-0.6B-Base · apache-2.0

Community card

MobiMind-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 card

systemone-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 card

system-one-mini

DavidHatley

distilbert-base-uncased fine-tuned to return typed decisions, 69M parameters.

69M · distilbert/distilbert-base-uncased · apache-2.0

Community card

plek-1

Drenel

A typed-decision model from Drenel, 783M parameters.

783M · apache-2.0

Community card

bert4jev

ukung

deberta-v3-large fine-tuned to return typed decisions, 434M parameters.

434M · microsoft/deberta-v3-large · apache-2.0

Community card

JevForge-0.8B

AndeyTait

Qwen3.5-0.8B fine-tuned to return typed decisions.

Qwen/Qwen3.5-0.8B · apache-2.0

Community card

Llama-3B-RLCD-SFT_Llama-3B-Flash_936_full_model

TaylorAI

A typed-decision model from TaylorAI.

Hugging Face

Community card

system-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 card

jev-0.5b

jaswanthsanjay88

A LoRA adapter that turns Qwen2.5-0.5B into a typed-decision model without shipping full weights.

Qwen/Qwen2.5-0.5B

Community card

system-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 card

system-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 card

laya-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 card

laya-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 card

laya-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 card

laya-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 card

decider-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 card

decider-35b-a3b-nvfp4

Mapika

A typed-decision model from Mapika, 18B parameters.

18B · Mapika/decider-35b-a3b · apache-2.0

Community card

laya-typed-decisions-mlx

aac6fef

laya-typed-decisions fine-tuned to return typed decisions, 421M parameters.

421M · convaiinnovations/laya-typed-decisions · apache-2.0

What we left out

Searching Hugging Face for this category turns up far more repositories than appear here. We dropped empty repositories with no weights, downloads or likes; exact copies of another account’s weights; and projects that only matched on a name, like a 3D scene model whose owner happens to be called Jev. Same-author variants trained differently were kept, because those are genuinely different models.

Everything that remains comes from each repository’s own metadata. A directory padded with entries nobody checked is worth less than a short one.

None of these were measured on your data

Public benchmarks tell you which models are worth a shortlist. They cannot tell you which one clears your error budget. That takes your own historical decisions, frozen into a test set.