GGUF · 101 models available
Run a decision model with llama.cpp
GGUF is the format that made local inference ordinary. For decision models it matters more than usual, because the whole argument for the category is cost per call.
How to run it
Install a runtime
llama.cpp is the reference implementation. Ollama wraps it if you would rather not build anything.
brew install llama.cppPull a model straight from Hugging Face
The -hf flag downloads and caches the GGUF without a separate step.
llama-cli -hf <owner>/<repo>Watch memory, not disk
A quantised 400M encoder is a few hundred megabytes on disk and runs comfortably on a laptop. The 2B and larger decoders are where you start caring about RAM.
Models available in GGUF
Every entry in the directory that ships this format, read from its repository metadata on2 November 2026.
Laya-GGUF
A GGUF build of laya, for running typed decisions on llama.cpp instead of a hosted API.
Jev-Style-Qwen3.5-2B-Decision-GGUF
A GGUF build of Jev-Style-Qwen3.5-2B-Decision, for running typed decisions on llama.cpp instead of a hosted API.
laya-GGUF
A GGUF build of laya, for running typed decisions on llama.cpp instead of a hosted API.
Jev-Style-0.8B-Decision-v3-GGUF
A GGUF build of Jev-Style-0.8B-Decision-v3, for running typed decisions on llama.cpp instead of a hosted API.
laya-multilingual-GGUF
A GGUF build of laya-multilingual, for running typed decisions on llama.cpp instead of a hosted API.
laya-gguf
A GGUF build of laya, for running typed decisions on llama.cpp instead of a hosted API.
pplx-decider-27B-Artemis-GGUF
A GGUF build of pplx-decider-27B-Artemis, for running typed decisions on llama.cpp instead of a hosted API.
jev
jev, an open-weight model published to return typed decisions, 882M parameters.
JEV-27B-VL-GGUF
A GGUF build of JEV-27B-VL, for running typed decisions on llama.cpp instead of a hosted API.
Jev-Omni-Q4_K_M-GGUF
A GGUF build of Jev-Omni, for running typed decisions on llama.cpp instead of a hosted API.
NeoHorse-Jev-4B-GGUF
A GGUF build of NeoHorse-Jev-4B, for running typed decisions on llama.cpp instead of a hosted API.
decider-2b-GGUF
A GGUF build of decider-2b, for running typed decisions on llama.cpp instead of a hosted API.
Jev-Style-2B-Decision-v3-GGUF
A GGUF build of Jev-Style-2B-Decision-v3, for running typed decisions on llama.cpp instead of a hosted API.
Jev-Style-Qwen3.5-2B-Decision-v2-GGUF
A GGUF build of Jev-Style-Qwen3.5-2B-Decision-v2, for running typed decisions on llama.cpp instead of a hosted API.
laya-typed-decisions-GGUF
A GGUF build of laya-typed-decisions, for running typed decisions on llama.cpp instead of a hosted API.
laya-multilingual-GGUF
A GGUF build of laya-multilingual, for running typed decisions on llama.cpp instead of a hosted API.
JEV-9B-GGUF
A GGUF build of JEV-9B, for running typed decisions on llama.cpp instead of a hosted API.
jev-Ternary-Bonsai-2-27B-Abliterated-PTQ1_0
A GGUF build of Ternary-Bonsai-2-27B-Abliterated-PTQ1_0-GGUF, for running typed decisions on llama.cpp instead of a hosted API.
JevK5-GGUF
A GGUF build of JevK5, for running typed decisions on llama.cpp instead of a hosted API.
Bonsai-JEV
Ternary-Bonsai-2-27B-gguf fine-tuned to return typed decisions, 27B parameters.
JEV-27B-GGUF
A GGUF build of JEV-27B, for running typed decisions on llama.cpp instead of a hosted API.
decider-4b-GGUF
A GGUF build of decider-4b, for running typed decisions on llama.cpp instead of a hosted API.
archai-jev-zagreus-0.4b-ita
zagreus-0.4B-ita fine-tuned to return typed decisions, 438M parameters.
decider-0.8b-GGUF
A GGUF build of decider-0.8b, for running typed decisions on llama.cpp instead of a hosted API.
decider-2b-vision-GGUF
A GGUF build of decider-2b-vision, for running typed decisions on llama.cpp instead of a hosted API.
embeddinggemma-2-ft-typed-decision-GGUF
A GGUF build of embeddinggemma-2-ft-typed-decision, for running typed decisions on llama.cpp instead of a hosted API.
Jev-Omni-GGUF
A GGUF build of Jev-Omni, for running typed decisions on llama.cpp instead of a hosted API.
laya-gguf-persian-multilingual-decision
A GGUF build of laya, for running typed decisions on llama.cpp instead of a hosted API.
decider-2b-GGUF
A GGUF build of decider-2b, for running typed decisions on llama.cpp instead of a hosted API.
decider-2b-vision-GGUF
A GGUF build of decider-2b-vision, for running typed decisions on llama.cpp instead of a hosted API.
pplx-decider-v1.1-27b-GGUF
A GGUF build of pplx-decider-v1.1-27b, for running typed decisions on llama.cpp instead of a hosted API.
JEV-27B-VL-GGUF
A GGUF build of JEV-27B-VL, for running typed decisions on llama.cpp instead of a hosted API.
decider-4b-GGUF
A GGUF build of decider-4b, for running typed decisions on llama.cpp instead of a hosted API.
decider-4b-v2-GGUF
A GGUF build of decider-4b-v2, for running typed decisions on llama.cpp instead of a hosted API.
jev-control-core
A GGUF build of Qwen3.5-0.8B-Base, for running typed decisions on llama.cpp instead of a hosted API.
jevify-gemma4-e4b-GGUF
A GGUF build of jevify-gemma4-e4b, for running typed decisions on llama.cpp instead of a hosted API.
laya-neutron-gguf
A GGUF build of laya, for running typed decisions on llama.cpp instead of a hosted API.
Gemma-4-12B-Unified-System-One-GGUF
A GGUF build of Gemma-4-12B-Unified-System-One, for running typed decisions on llama.cpp instead of a hosted API.
decider-35b-a3b-GGUF
A GGUF build of decider-35b-a3b, for running typed decisions on llama.cpp instead of a hosted API.
EXAONE-4.0-1.2B-JEV-GGUF
A GGUF build of EXAONE-4.0-1.2B-JEV, for running typed decisions on llama.cpp instead of a hosted API.
laya-multilingual-gguf
A GGUF build of laya-multilingual, for running typed decisions on llama.cpp instead of a hosted API.
JEV-27B-VL-Uncensored-GGUF
A GGUF build of JEV-27B-VL-Uncensored, for running typed decisions on llama.cpp instead of a hosted API.
Jev_Qwen3.8-27B-GGUF
A GGUF build of Jev_Qwen3.8-27B, for running typed decisions on llama.cpp instead of a hosted API.
jevify-gemma4-26b-a4b-GGUF
A GGUF build of jevify-gemma4-26b-a4b, for running typed decisions on llama.cpp instead of a hosted API.
laya-mm-guard-v3-gguf
A GGUF build of laya-multilingual, for running typed decisions on llama.cpp instead of a hosted API.
laya-multilingual-F16-GGUF
A GGUF build of laya-multilingual, for running typed decisions on llama.cpp instead of a hosted API.
laya-v796
laya fine-tuned to return typed decisions, 421M parameters.
LFM2.5-350M-RLCD-GGUF
A GGUF build of LFM2.5-350M-RLCD, for running typed decisions on llama.cpp instead of a hosted API.
local-typed-decisions
A GGUF build of Qwen3-4B, for running typed decisions on llama.cpp instead of a hosted API.
Jev-Style-2B-Decision-v3-GGUF
A GGUF build of Jev-Style-2B-Decision-v3, for running typed decisions on llama.cpp instead of a hosted API.
OOMU-SystemOne-0.6B-GGUF
OOMU-SystemOne-0.6B-GGUF, an open-weight model published to return typed decisions, 596M parameters.
OpenThai-SystemOne-GGUF
A GGUF build of OpenThai-SystemOne, for running typed decisions on llama.cpp instead of a hosted API.
OpenThai-SystemOne-Ollama
OpenThai-SystemOne fine-tuned to return typed decisions, 752M parameters.
JEV-27B-VL-GGUF
A GGUF build of JEV-27B-VL, for running typed decisions on llama.cpp instead of a hosted API.
statim-decide-multilingual-base
laya-multilingual fine-tuned to return typed decisions, 322M parameters.
statim-decide-multilingual-base-pii
statim-decide-multilingual-base fine-tuned to return typed decisions, 3M parameters.
statim-decide-multilingual-base-safety
statim-decide-multilingual-base fine-tuned to return typed decisions, 3M parameters.
xDecision
laya-multilingual fine-tuned to return typed decisions.
laya-gguf
A GGUF build of laya, for running typed decisions on llama.cpp instead of a hosted API.
aemeath-systemone-kev
aemeath-systemone-kev, an open-weight model published to return typed decisions, 752M parameters.
aimtas-laya-multilingual-GGUF
A GGUF build of laya-multilingual, for running typed decisions on llama.cpp instead of a hosted API.
laya-multilingual-GGUF
A GGUF build of laya-multilingual, for running typed decisions on llama.cpp instead of a hosted API.
ara-jev-Faisal-GGUF
A GGUF build of ara-jev-Faisal, for running typed decisions on llama.cpp instead of a hosted API.
archai-jev-games-1.5b-v2
archai-jev-qwen-1.5b fine-tuned to return typed decisions, 1.5B parameters.
archai-jev-qwen-1.5b
Qwen2.5-1.5B-Instruct fine-tuned to return typed decisions, 1.5B parameters.
decider-0.8b-GGUF
A GGUF build of decider-0.8b, for running typed decisions on llama.cpp instead of a hosted API.
bit-jev-2b-distilled
A GGUF build of bitnet-b1.58-2B-4T-bf16, for running typed decisions on llama.cpp instead of a hosted API.
Coral-decider-4b-GGUF
A GGUF build of Coral-decider-4b, for running typed decisions on llama.cpp instead of a hosted API.
decider-0.8b-Q8
A GGUF build of decider-0.8b, for running typed decisions on llama.cpp instead of a hosted API.
decider-0.8b-GGUF
A GGUF build of decider-0.8b, for running typed decisions on llama.cpp instead of a hosted API.
decider-2b-GGUF
A GGUF build of decider-2b, for running typed decisions on llama.cpp instead of a hosted API.
NeoHorse-Jev-4B-GGUF
A GGUF build of NeoHorse-Jev-4B, for running typed decisions on llama.cpp instead of a hosted API.
edceleste-decider-0.8b-GGUF
A GGUF build of edceleste-decider-0.8b, for running typed decisions on llama.cpp instead of a hosted API.
elythros-decider-0.6b-GGUF
A GGUF build of elythros-decider-0.6b, for running typed decisions on llama.cpp instead of a hosted API.
laya-typed-decisions-gguf
A GGUF build of laya-typed-decisions, for running typed decisions on llama.cpp instead of a hosted API.
Gemma-4-12B-Unified-System-One-GGUF
A GGUF build of Gemma-4-12B-Unified-System-One, for running typed decisions on llama.cpp instead of a hosted API.
decider-2b-GGUF
A GGUF build of decider-2b, for running typed decisions on llama.cpp instead of a hosted API.
JEV-27B-Uncensored-GGUF
A GGUF build of JEV-27B-Uncensored, for running typed decisions on llama.cpp instead of a hosted API.
JEV-35B-GGUF
A GGUF build of JEV-35B, for running typed decisions on llama.cpp instead of a hosted API.
jev-japanese-judgment
LFM2.5-1.2B-JP-202606 fine-tuned to return typed decisions, 3M parameters.
jev-novel-2.5-0.8b-GGUF
A GGUF build of jev-novel-2.5-0.8b-bf16, for running typed decisions on llama.cpp instead of a hosted API.
jev-novel-2.5-4b-GGUF
A GGUF build of jev-novel-2.5-4b-bf16, for running typed decisions on llama.cpp instead of a hosted API.
jev-student-4b-yizao
A GGUF build of Qwen3.5-4B-Base, for running typed decisions on llama.cpp instead of a hosted API.
jev-vlm-4b-lite-gguf
A GGUF build of jev-vlm-4b-lite, for running typed decisions on llama.cpp instead of a hosted API.
laya-finetuned-rlcd-GGUF
A GGUF build of laya, for running typed decisions on llama.cpp instead of a hosted API.
laya-modernbert-decision-90pct
laya fine-tuned to return typed decisions, 421M parameters.
llm-jp-4.1-33b-systemone-experimental
llm-jp-4.1-33b-thinking fine-tuned to return typed decisions, 33B parameters.
MacJev-322M-4K-Laya-GGUF
A GGUF build of MacJev-322M-4K-Laya, for running typed decisions on llama.cpp instead of a hosted API.
decider-0.8b-GGUF
A GGUF build of decider-0.8b, for running typed decisions on llama.cpp instead of a hosted API.
MobiMind-Decider-7B-GGUF
A GGUF build of MobiMind-Decider-7B, for running typed decisions on llama.cpp instead of a hosted API.
JEV-9B-GGUF
A GGUF build of JEV-9B, for running typed decisions on llama.cpp instead of a hosted API.
laya-multilingual-GGUF
A GGUF build of laya-multilingual, for running typed decisions on llama.cpp instead of a hosted API.
Sakura-Humanlike-Chat-2.0-JEV-AutoRound-GGUF
A GGUF build of JEV-27B, for running typed decisions on llama.cpp instead of a hosted API.
laya-GGUF
A GGUF build of laya, for running typed decisions on llama.cpp instead of a hosted API.
sarashina2.2-vision-3b-mmproj-jev-f16
A GGUF build of sarashina2.2-vision-3b, for running typed decisions on llama.cpp instead of a hosted API.
decider-0.8b-GGUF
A GGUF build of decider-0.8b, for running typed decisions on llama.cpp instead of a hosted API.
Solar-JEV-Gemma-embed-2-GGUF
A GGUF build of Solar-JEV-Gemma-embed-2, for running typed decisions on llama.cpp instead of a hosted API.
statim-decide-multilingual-base-actions
statim-decide-multilingual-base fine-tuned to return typed decisions, 3M parameters.
statim-decide-multilingual-base-emotion
statim-decide-multilingual-base fine-tuned to return typed decisions, 3M parameters.
strands-decider-2B-hobson-v19-GGUF
A GGUF build of strands-decider-2B-hobson-v19, for running typed decisions on llama.cpp instead of a hosted API.
voice-decisions-laya-v4
laya fine-tuned to return typed decisions, 421M parameters.
Also browsable as a facet of the directory: GGUF builds.
Other ways to run one
MLX
MLX uses unified memory on M-series chips. For a model in the few-hundred-megabyte range this is the fastest local option on a Mac, and it needs no GPU of its own.
ONNX
An ONNX export loads without PyTorch. That matters for slim containers, for edge devices, and for running a decision inside a browser.
Core ML
Core ML puts the model on the Neural Engine, so the decision happens on the phone or the laptop and nothing leaves it. The strongest privacy story in the category.
Compatible servers
16 open projects that reimplement the decision API, if you want the interface rather than just the weights.
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.