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
ME
Mellum2 12B A2.5B Thinking
Mellum · JetBrains
Params12.1B
Context128K
Q4_K_M8.1 GB
Reasoning
DE
DeepSeek R1 Distill Llama 70B Abliterated GGUF ARMADO
DeepSeek · Thaurock
Params70.6B
Context128K
Q4_K_M42.5 GB
Reasoning
GE
Gemma 4 31B IT NVFP4
Gemma · esatapedico
Params30.7B
Context256K
Smallest17.3 GB
ReasoningTool use
OB
MN Oblivion 26B UNCENSORED NEO Imatrix
Oblivion · DavidAU
Params25.6B
Context1000K
Q4_K_M16.3 GB
ReasoningRoleplay
ON
OneJev1.6 0.8B
Onejev · mradermacher
Params752M
Context256K
Q4_K_M0.5 GB
ReasoningTool useVision
JU
Jugurtha 2 9B
Jugurtha · mradermacher
Params9.2B
Context256K
Q4_K_M5.8 GB
ReasoningTool use
LL
Llama 3.1 8B Magpie Align SFT v0.1
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
Reasoning
QW
MANGO Qwen3 Omni 30B A3B Instruct
Qwen · mradermacher
Params30.5B
Context64K
Q4_K_M18.6 GB
ReasoningTool useVision
QW
ThinkingCap Qwen3.8 27B Uncensored Heretic
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
Reasoning
NE
Nemotron Cascade 14B Thinking
Nemotron · bartowski
Params14.8B
Context32K
Q4_K_M9.0 GB
Reasoning
QW
Qwen3.8 27B TURBO Fable Cold Fusion 735 882 Heretic Uncensored NEO CODER MAX MTP
Qwen · diablomike20
Params26.9B
Context256K
Q4_K_M18.0 GB
CodingReasoningRoleplay
HA
Harmonic Hermes 9B
Harmonic · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool use
OP
OpenThinker Agent v1
Openthinker · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
CodingReasoningTool use
QW
shisa v2.1 qwen3 8b UD japanese imatrix
Qwen · dahara1
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
QW
QwQ 32B
Qwen · duyntnet
Params32.8B
Context40K
Q4_K_M19.9 GB
ReasoningTool use
QW
Qwen3.8 27B Halloween Terror Heretic Uncensored Source
Qwen · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
ReasoningRoleplayTool use
QW
Qwen3.8 27B OrcaRouter Uncensored MTP
Qwen · codavidgarcia
Params27.3B
Context256K
Smallest10.9 GB
ReasoningTool use
NE
Nemotron Cascade 2 30B A3B
Nemotron · mradermacher
Params31.6B
Context1024K
Q4_K_M24.5 GB
Reasoning
QW
Qwen3.6 27B Heretic2 Uncensored Finetune Thinking
Qwen · mradermacher
Params26.9B
Context256K
Q4_K_M16.5 GB
ReasoningRoleplayTool use
QW
SVD Qwen3 Coder Next Thinking
Qwen · mradermacher
Params79.7B
Context256K
Q4_K_M48.5 GB
CodingReasoningTool use
QW
Qwen3 Esper3 Reasoning CODER Instruct 21B Brainstorm20x 128k Ctx
Qwen · mradermacher
Params21B
Context128K
Q4_K_M12.8 GB
CodingReasoning
QW
Qwen3 4B Claude Sonnet 4 Reasoning Distill Heretic Abliterated Heretic Abliterated
Qwen · Kirill777Vais
Params4.02B
Context40K
Q4_K_M2.5 GB
ReasoningTool use
DA
L3.1 Dark Reasoning Dark Planet Hermes R1 Uncensored Horror Imatrix MAX 8B
Dark · DavidAU
Params8B
Context128K
Q4_K_M5.5 GB
ReasoningRoleplayTool use
GE
Gemma3 27B It Vl GLM 4.7 Uncensored Heretic Deep Reasoning
Gemma · mradermacher
Params27B
Context128K
Q4_K_M16.5 GB
ReasoningVision
MI
allura org Mistral Small 24b Sertraline 0304
Mistral · bartowski
Params23.6B
Context32K
Q4_K_M14.3 GB
CodingReasoning
MI
Mixtral AI Ultron
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
CodingReasoningRoleplay
QW
Kataguru Sceptic 35B A3B v2.8.1 BF16
Qwen · kataguru
Params35.2B
Context256K
Smallest12.9 GB
ReasoningTool useVision
ME
MedicalQwen3 Reasoning 14B IT
Medicalqwen · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
ReasoningTool use
QW
Qwen3.5 0.8B
Qwen · mradermacher
Params752M
Context256K
Q4_K_M0.5 GB
ReasoningTool useVision
DE
Qwen3 30B A3B Thinking 2507 Deepseek v3.1 Distill V2 FP32
DeepSeek · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
CodingReasoning

Other uses

Keep browsing