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
FN
FNova 1.7B Chat v1
Fnova · mradermacher
Params1.72B
Context32K
Q4_K_M1.1 GB
ReasoningTool use
CH
CHIMERA 4B RL
Chimera · mradermacher
Params4.41B
Context256K
Q4_K_M2.7 GB
Reasoning
OR
Ornstein 122 A10B
Ornstein · mradermacher
Params122B
Context256K
Q4_K_M74.2 GB
ReasoningVision
GE
Gemma 3 12b It Vl GPT 5.1 High Heretic Uncensored Thinking
Gemma · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
ReasoningVision
QW
Qwen3 30B A3B YOYO V2 Claude 4.6 Opus High INSTRUCT
Qwen · mradermacher
Params30.5B
Context986K
Q4_K_M18.6 GB
Reasoning
SO
Solar JEV 27B R32
Solar · SargeDev
Params27.3B
Context256K
Q4_K_M16.8 GB
ReasoningTool use
MI
Mistral Nemo Instruct 2407 12B Thinking HI Claude Opus High Reasoning
Mistral · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
ReasoningRoleplay
QW
Qwen3.8 27B TURBO
Qwen · Psjuan
Params27B
Context256K
Q4_K_M18.0 GB
CodingReasoningRoleplay
AT
ATLAS 8B Thinking
Atlas · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
Reasoning
QW
Qwen3.8 27B Heretic
Qwen · cu64
Params26.9B
Context256K
Q4_K_M18.0 GB
CodingReasoningRoleplay
GE
Gemma 3 12b It Vl GLM 4.7 Flash Heretic Uncensored Thinking
Gemma · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
ReasoningVision
NE
OpenReasoning Nemotron 14B
Nemotron · bartowski
Params14.8B
Context128K
Q4_K_M9.0 GB
Reasoning
AM
AmoreLLM 4B
Amorellm · mradermacher
Params4.02B
Context32K
Q4_K_M2.5 GB
ReasoningTool use
VE
Veloxy Titan 32B Vision
Veloxy · mradermacher
Params26.9B
Context256K
Q4_K_M16.5 GB
CodingReasoningVision
DA
Dark Craving 26B A4B v0.2
Dark · ReadyArt
Params25.2B
Context256K
Q4_K_M16.8 GB
ReasoningRoleplayTool use
QW
Qwen3.8 27B TURBO Fable Cold Fusion 735 882 Heretic Uncensored NEO CODER MAX MTP
Qwen · sky3c
Params27B
Context256K
Q4_K_M18.0 GB
CodingReasoningRoleplay
QW
Qwen3.5 21B Claude 4.6 Opus Deckard Heretic Uncensored Thinking
Qwen · mradermacher
Params20.8B
Context256K
Q4_K_M12.9 GB
CodingReasoningRoleplay
QW
Qwen3.8 27b Noslop
Qwen · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
ReasoningTool useVision
QW
Qwen3.5 2B Artemis
Qwen · turintech
Params1.88B
Context256K
Q4_K_M1.3 GB
ReasoningTool useVision
MI
Mistral 2x24B MOE Power Devstral Magistral Reasoning Ultimate 44B
Mistral · mradermacher
Params43.7B
Context128K
Q4_K_M26.5 GB
CodingReasoning
QW
Qwen3.8 max Reasoning Distilled
Qwen · khazarai
Params773M
Context256K
Q4_K_M0.5 GB
ReasoningVision
OY
OYM Qimi 122B A10B K2.6
Oym · mradermacher
Params125B
Context256K
Q4_K_M75.8 GB
ReasoningTool useVision
MI
MiniCPM5 1B Heretic
MiniCPM · saidutta69
Params1.08B
Context128K
Q4_K_M0.7 GB
ReasoningTool use
AV
Avicenna 8B Base
Avicenna · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
Reasoning
QW
Qwen3.8 2B Heretic
Qwen · mradermacher
Params1.88B
Context256K
Q4_K_M1.3 GB
ReasoningTool useVision
QW
OPSD Qwen3 4B
Qwen · mradermacher
Params4.41B
Context40K
Q4_K_M2.7 GB
Reasoning
LL
Llama 3.1 Storm 8B
Llama · legraphista
Params8B
Context128K
Smallest2.0 GB
Reasoning
QW
Qwen3.8 27B TTURBO Cold Fusion 709 L NM DAU UltraOptimised VariableThinking
Qwen · Solstice-AI
Params27B
Context256K
Q4_K_M16.5 GB
CodingReasoningRoleplay
CH
CHIMERA 4B SFT
Chimera · mradermacher
Params4B
Context256K
Q4_K_M2.5 GB
Reasoning
QW
Qwen3.6 27B OBLITERATED
Qwen · DRV58
Params26.9B
Context256K
Q4_K_M16.5 GB
ReasoningTool use

Other uses

Keep browsing