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
MO
Steelskull L3.3 Mokume Gane R1 70b v1.1
Mokume · bartowski
Params70.6B
Context128K
Q4_K_M42.5 GB
Reasoning
QW
Qwen3 VL 4B Thinking Abliterated v1
Qwen · prithivMLmods
Params4B
Context256K
Q4_K_M2.5 GB
ReasoningVision
QW
NOVER1 Qwen2.5 7B
Qwen · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
Reasoning
QW
Qwen3 Coder 42B A3B Instruct TOTAL RECALL MASTER CODER M
Qwen · mradermacher
Params42.4B
Context256K
Q4_K_M25.7 GB
CodingReasoningTool use
GE
Huihui Gemma 4 12B Agentic Fable5 Abliterated
Gemma · mradermacher
Params11.9B
Context256K
Q4_K_M7.4 GB
CodingReasoning
GE
Gemma 4 E4B It The DECKARD Claude Opus Expresso Universe HERETIC UNCENSORED Thinking
Gemma · mradermacher
Params7.5B
Context128K
Q4_K_M5.3 GB
CodingReasoningRoleplay
DE
FuseO1 DeepSeekR1 QwQ SkyT1 Flash 32B Preview
DeepSeek · bartowski
Params32.8B
Context128K
Q4_K_M19.9 GB
Reasoning
QW
Qwen3.6 27B Uncensored Aggressive
Qwen · mradermacher
Params26.9B
Context256K
Q4_K_M16.5 GB
ReasoningTool use
LF
LFM2.5 2.6B DSpark Draft v1
Lfm · magnitudedev
Params328M
Context125K
Smallest0.4 GB
ReasoningTool use
MI
Ministral 3 14B Reasoning 2512 ShiningValiant3
Mistral · mradermacher
Params13.5B
Context256K
Q4_K_M8.2 GB
CodingReasoning
TU
DR Tulu SFT 8B
Tulu · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
GO
Goose 7.2B G1k 20261007
Goose · mradermacher
Params7.2B
Context1024K
Q4_K_M4.5 GB
ReasoningTool use
OM
OmniCoder 9B Claude Opus High Reasoning Distill
Omnicoder · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
CodingReasoningVision
AL
ALIA 40b Instruct 2601
Alia · mradermacher
Params40.4B
Context160K
Q4_K_M24.6 GB
Reasoning
QW
Qwopus3.5 4B Coder
Qwopus · mradermacher
Params4.33B
Context256K
Q4_K_M2.8 GB
CodingReasoningTool use
MI
MicroThinker 3B Preview
Microthinker · mradermacher
Params3.21B
Context128K
Q4_K_M2.0 GB
Reasoning
AG
Agri 31b v1
Agri · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
ReasoningTool useVision
QW
Qwen3.8 27B Coder390 EfficientThink Opus5.5 GPT6Astra Grok4.7 DSV4Pro K3 SFT RLOO MTP DFlash2
Qwen · kejizilu
Params27.3B
Context256K
Smallest3.2 GB
CodingReasoningTool use
QW
Qwen3.5 9B Claude 4.6 Opus Deckard V4.2 Uncensored Heretic Thinking
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningRoleplayVision
QW
MathSmith HC Qwen3 14B ShortCoT
Qwen · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
ReasoningTool use
LF
LFM2.5 VL 3B heretic
Lfm · saidutta69
Params2.7B
Context32K
Q4_K_M1.7 GB
CodingReasoningTool use
QW
VibeThinker 3B heretic
Qwen · saidutta69
Params3.09B
Context128K
Q4_K_M1.9 GB
CodingReasoningTool use
DE
DeepSeek R1 Distill Qwen 14B Abliterated v2
DeepSeek · mradermacher
Params14.8B
Context128K
Q4_K_M9.0 GB
Reasoning
QW
Qwen3 8B 64k Context 2X Medium
Qwen · mradermacher
Params8.19B
Context64K
Q4_K_M5.0 GB
Reasoning
QW
Qwen3 4B Opus 5.5
Qwen · KomorAI
Params4.02B
Context40K
Q4_K_M2.5 GB
ReasoningTool use
XO
XORTRON AgentRICO
Xortron · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
ReasoningTool useVision
FL
Flint APEX I NanoPlus V2.1
Flint · IsValorum
Params39.8B
Context256K
Smallest13.2 GB
CodingReasoningTool use
QW
Qwen3.5 4B Medical Reasoning
Qwen · xtools-at
Params4.2B
Context256K
Q4_K_M2.7 GB
ReasoningVision
QW
Qwen3.5 4B Opus Distil
Qwen · reaperdoesntknow
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool useVision
DE
Josiefied DeepSeek R1 0528 Qwen3 8B Abliterated v1
DeepSeek · mradermacher
Params8.19B
Context128K
Q4_K_M5.0 GB
Reasoning

Other uses

Keep browsing