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
QW
Qwopus3.8 27B Flash V2
Qwopus · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
CodingReasoningTool use
MI
Mistral 2x24B MOE Magistral 2506 Devstral 2507 1.1 Coder Reasoning Ultimate 44B
Mistral · mradermacher
Params43.7B
Context128K
Q4_K_M26.5 GB
CodingReasoning
MI
Mistral Large 4 1T A52B NVFP4
Mistral · ggml-org
Params1050B
Context1024K
Smallest4.2 GB
ReasoningTool useVision
QW
Suri Qwen 3.5 9B Uncensored
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool use
QW
Qwen3.6 35B A3B mlx claude coder abliterated
Qwen · rafw007
Params36B
Context256K
Q4_K_M23.9 GB
CodingReasoningTool use
FR
Friday 35B
Friday · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
CodingReasoningTool use
GE
Gemma-4-The-Deckards-Brain-31b
Gemma · kabachuha
Params30.7B
Context256K
Q4_K_M18.7 GB
ReasoningRoleplayVision
HE
G Health 14B Instruct
Health · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
ReasoningTool use
QW
Qwen36 35B Opus Reasoning Merged
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
Reasoning
QW
Dongfangshuo Qwen3.8 27B NSFW Novel
Qwen · mradermacher
Params26.9B
Context256K
Q4_K_M16.5 GB
ReasoningRoleplayTool use
MI
DeepHermes 3 Mistral 24B Preview
Mistral · NousResearch
Params23.6B
Context32K
Smallest13.4 GB
ReasoningRoleplayTool use
LL
Llama 3.2 8X3B GATED MOE Reasoning Dark Champion Instruct uncensored abliterated 18.4B
Llama · DavidAU
Params18.4B
Context128K
Q4_K_M11.4 GB
ReasoningRoleplay
QW
Qwen3.5 9B Ultra Heretic
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool useVision
HE
Heimdallr 27B v0.35
Heimdallr · ReadyArt
Params27.3B
Context256K
Q4_K_M16.8 GB
ReasoningRoleplayTool use
GE
MamayLM Gemma 3 12B IT v1.0
Gemma · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
Reasoning
LL
Llama 3.3 8B Instruct Thinking Claude Haiku 4.5 High Reasoning 1700x
Llama · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
ReasoningRoleplayTool use
GE
Gemma 4 E2B It GMCE
Gemma · mradermacher
Params4.65B
Context128K
Q4_K_M3.4 GB
ReasoningTool useVision
QW
Qwen3.5 2B Polaris HighIQ INSTRUCT
Qwen · mradermacher
Params1.88B
Context256K
Q4_K_M1.3 GB
ReasoningTool use
CA
CantoneseLLM v2.0 30B A3B Thinking Chat Vector Merged
Cantonesellm · mradermacher
Params30.5B
Context40K
Q4_K_M18.6 GB
Reasoning
DE
DeepSeek R1 Distill Qwen 1.5B Fully Uncensored
DeepSeek · 234-45Qq
Params1.78B
Context128K
Smallest1.3 GB
Reasoning
QW
Qwen3.8-27B
Qwen · XGeorgeCostanzaX
Params26.9B
Context256K
Smallest8.0 GB
ReasoningTool use
QW
SatellaRAG 0.8B
Qwen · EphAsad
Params773M
Context256K
Q4_K_M0.5 GB
ReasoningVision
MI
Ministral 3 8B Reasoning 2512 Uncensored
Mistral · mradermacher
Params8.49B
Context256K
Q4_K_M5.2 GB
ReasoningTool useVision
QW
Qwen3.5 4B Claude 4.6 HighIQ THINKING
Qwen · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningRoleplayTool use
ST
G4 Starry Ocean 12B
Starry · mradermacher
Params11.9B
Context256K
Q4_K_M7.4 GB
ReasoningRoleplayTool use
QW
Qwen3 Yoyo V4 42B A3B Thinking TOTAL RECALL PDK V
Qwen · mradermacher
Params42.4B
Context256K
Q4_K_M25.7 GB
CodingReasoningTool use
DE
DeepSeek R1 Zero BF16
DeepSeek · unsloth
Params671B
Context160K
Q4_K_M404.4 GB
Reasoning
CY
Cyber Ornith 1.5 9B OBLITERATED
Cyber · Atomic-Germ
Params8.95B
Context256K
Q4_K_M5.6 GB
CodingReasoningTool use
RU
Rumeni 26B A4B
Rumeni · mradermacher
Params26B
Context256K
Q4_K_M17.2 GB
ReasoningRoleplayTool use
QW
Shrey Ai 2 27B
Qwen · MRSHREY197
Params26.9B
Context256K
Smallest5.9 GB
ReasoningTool useVision

Other uses

Keep browsing