Reasoning GGUF models
46569 GGUF models: models that think step by step before answering. Sizes run from 1M to 5376B parameters. The longest trained context is 5120K tokens.
QW
Qwen3 0.6B
Qwen · lm-kit
Params752M
Context40K
Q4_K_M0.5 GB
MI
Ministral 3 8B Reasoning 2512 Uncensored
Mistral · mradermacher
Params8.49B
Context256K
Q4_K_M5.2 GB
NE
NeoHorse 1 9 Uncensored
Neohorse · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
RA
RACRO 7B CRO GRPO
Racro · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
AV
AVAR Thinker 7B
Avar · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
LF
LFM2.5 24B A2B
Lfm · m9ter1a
Params24B
Context128K
Q4_K_M15.0 GB
GE
Gemma3 Code Reasoning 4B
Gemma · mradermacher
Params3.88B
Context128K
Q4_K_M2.5 GB
DE
DeepSeek R1 Distill Qwen 14B Uncensored Reasoner
DeepSeek · mradermacher
Params14.8B
Context128K
Q4_K_M9.0 GB
BE
Behemoth 128B v3
Behemoth · mradermacher
Params125B
Context256K
Q4_K_M74.9 GB
QW
Qwen3 VL 30B A3B Thinking
Qwen · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
QW
Huihui Qwen3 Omni 30B A3B Captioner Abliterated
Qwen · mradermacher
Params30.5B
Context64K
Q4_K_M18.6 GB
DE
Devstral Small 2505 Deepseek V3.2 Speciale Distill
DeepSeek · TeichAI
Params23.6B
Context128K
Q4_K_M14.3 GB
QW
OpenYourMind Qwen3.6 35B A3B Kuato DPO Abliterated Uncensored
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
QW
Qwen3.5 9B Distill Qwen 3.8 Flash 20261011
Qwen · kevinzhou21
Params9.2B
Context256K
Q4_K_M5.8 GB
AP
Apertus 8B Instruct 2509 Heretic
Apertus · mradermacher
Params8.05B
Context64K
Q4_K_M5.1 GB
MI
Ministral 3 3B Reasoning 2512 Heretic
Mistral · coder3101
Params3.43B
Context256K
Q4_K_M2.1 GB
SP
Spark X2.6 4b Abliterated
Spark · FrostWolfAI
Params4.11B
Context1024K
Q4_K_M2.6 GB
QW
DFlash Qwen3.5 27B Uncensored
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
QW
Huihui Qwen3 4B Thinking 2507 Abliterated
Qwen · mradermacher
Params4.02B
Context256K
Q4_K_M2.5 GB
MI
OPSD MiniCPM4.1 8B
MiniCPM · mradermacher
Params8.19B
Context64K
Q4_K_M5.0 GB
QW
Qwen3.8-27B-Candor-Uncensored
Qwen · candor-lab
Params27.3B
Context256K
Q4_K_M16.8 GB
QW
Huihui ai.Qwen3 30B A3B Abliterated
Qwen · DevQuasar-15
Params30.5B
Context40K
Q4_K_M18.6 GB
SA
Steelskull L3.3 San Mai R1 70b
San · bartowski
Params70.6B
Context128K
Q4_K_M42.5 GB
QW
Octen WebGR 0.6B imatrix
Qwen · liodon-ai
Params730M
Context32K
Q4_K_M0.5 GB
QW
Qwen3.8 27B Unleashed
Qwen · Prolokkmn
Params26.9B
Context256K
Q4_K_M16.5 GB
QW
Qwen3.6 35B A3B Abliterated MAX
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
GE
Gemma-4-E4B-Uncensored-HauhauCS-Aggressive
Gemma · aoiandroid
Params7.52B
Context128K
Q4_K_M5.3 GB
MI
MiniMax M3.1 Flash Q2 K
Minimax · smalinin
Params2.12B
Context1024K
Smallest3.9 GB
RU
RusMind Vspyshka 4.7
Rusmind · mradermacher
Params7.52B
Context128K
Q4_K_M5.3 GB
HO
Holo2 8B
Holo · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB