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.

Most downloadedNewestLargestLongest contextSmallest
MI
Ministral 3 3B Claude Opus Reasoning Distilled
Mistral · mradermacher
Params3.43B
Context256K
Q4_K_M2.1 GB
Reasoning
GP
Gpt Oss 20b
gpt-oss · DavidAU
Params20.9B
Context128K
Smallest11.5 GB
CodingReasoning
QW
GrayLine Qwen3 8B
Qwen · bartowski
Params8.19B
Context40K
Q4_K_M5.0 GB
Reasoning
QW
Qwen3 Omni 30B A3B Instruct
Qwen · steampunque
Params30.5B
Context64K
Smallest16.9 GB
ReasoningTool useVision
FL
flint APEX
Flint · mudler
Params39.8B
Context256K
Smallest14.8 GB
ReasoningTool use
NO
Novel Humanize 4b
Novel · mradermacher
Params4.02B
Context40K
Q4_K_M2.5 GB
ReasoningTool use
TO
ToolSpace 8B
Toolspace · mradermacher
Params8.19B
Context64K
Q4_K_M5.0 GB
ReasoningTool use
OT
Other Test GGUFs
Other · ToastyPigeon
Params27.3B
Context256K
Smallest9.5 GB
ReasoningTool use
QW
Qwen3.6 35B A3B 2Bit GSQ RCO
Qwen · chtisgit
Params31.6B
Context256K
Smallest11.6 GB
ReasoningTool useVision
QW
Qwen3.6 35B A3B Brainwaves Nex Uncensored
Qwen · mradermacher
Params35.5B
Context256K
Q4_K_M21.7 GB
Reasoning
MI
mistralai_Ministral 3 8B Reasoning 2512
Mistral · lmstudio-community
Params8.49B
Context256K
Q4_K_M5.2 GB
ReasoningVision
MI
Huihui MiniCPM V 4.6 Thinking Abliterated
MiniCPM · mradermacher
Params752M
Context256K
Q4_K_M0.5 GB
ReasoningVision
QW
SignOfFour
Qwen · mradermacher
Params34.7B
Context32K
Q4_K_M21.2 GB
CodingReasoning
VU
VulnLLM R 7B
Vulnllm · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
CodingReasoning
MI
Magistral-Small-2509
Mistral · lmstudio-community
Params23.6B
Context128K
Q4_K_M14.3 GB
ReasoningVision
GE
Gemma 4 E2B It Uncensored MAX
Gemma · mradermacher
Params4.65B
Context128K
Q4_K_M3.4 GB
Reasoning
QW
Qwopus3.5 4B v3
Qwen · Jackrong
Params4.2B
Context256K
Q4_K_M2.7 GB
ReasoningVision
QW
Qwen3 VL 32B Thinking
Qwen · bartowski
Params32.8B
Context256K
Q4_K_M19.8 GB
ReasoningVision
MA
Marco Mini Instruct
Marco · mradermacher
Params17.3B
Context32K
Q4_K_M10.5 GB
Reasoning
QW
Qwen3.8 27B Q8 0
Qwen · Chungulus
Params27.3B
Context256K
Smallest29.0 GB
ReasoningTool useVision
FL
Flux 3 Image Klein Pup
Flux · ND911
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool useVision
QW
Qwen3 30B A3B Claude 4.5 Opus High Reasoning 2507 ABLITERATED UNCENSORED V2
Qwen · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
Reasoning
ER
ERNIE 21B A3B Claude 4.5 High OPUS Thinking
Ernie · mradermacher
Params21.8B
Context128K
Q4_K_M13.2 GB
Reasoning
GE
Gemma 4 31B It Claude Opus Distill
Gemma · TeichAI
Params30.7B
Context256K
Q4_K_M18.7 GB
ReasoningVision
NA
Nanbeige4.3 33B
Nanbeige · mradermacher
Params33.1B
Context512K
Q4_K_M20.1 GB
ReasoningTool use
SA
GGUF.chatgpt gpt codex V2
Safetensors · mondk
Params4B
Context256K
Q4_K_M2.5 GB
Reasoning
GL
L3 V2 S M B Grand HORROR 17B GLM4.7 Thinking UNCENSORED NEO Imatrix
GLM · DavidAU
Params16.5B
Context8K
Q4_K_M10.1 GB
ReasoningRoleplay
QW
Qwen3.5 9B Unredacted MAX
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
Reasoning
QW
Qwen3 30B A3B Thinking 2507 FT
Qwen · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
Reasoning
GE
Gemma 4 31B It Claude Opus Distill v2 Heretic
Gemma · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
Reasoning

Other uses

Keep browsing