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
Qwen3.8 Flash Next Avalon
Qwen · freriadoc
Params107B
Context256K
Smallest1.5 GB
ReasoningTool use
DE
DeepSeek R1 Codegeneration COT
DeepSeek · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
CodingReasoning
CY
Cyber Ornith 1.5 9B OBLITERATED
Cyber · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
CodingReasoningTool use
QW
Qwen3.8 27B TWIN TURBO Fable Cold Fusion 709 ULTRA HERETIC Uncensored NM DAU NEO MTP
Qwen · Zyszztggd
Params27B
Context—
Q4_K_M18.0 GB
CodingReasoningRoleplay
QW
Qwen3.8 27b Noslop
Qwen · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
ReasoningTool use
B4
B4 27B i1
mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
ReasoningTool use
ON
OneJev1.6 9B
Onejev · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool useVision
QW
UniReason Qwen3 14B No Think SFT
Qwen · mradermacher
Params14.8B
Context32K
Q4_K_M9.0 GB
Reasoning
QW
Qwen3.5 4B Heretic 2xMerge DavidAU
Qwen · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningVision
QW
shisa v2.1 qwen3 8b
Qwen · XpressAI
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
QW
Huihui Qwen3 Coder Next Opus 4.6 Reasoning Distilled abliterated
Qwen · Momix-44
Params80B
Context256K
Q4_K_M48.5 GB
CodingReasoning
DE
Vigyan 1.5B 4x MoE
DeepSeek · shreyansh12183
Params6.4B
Context128K
Q4_K_M3.9 GB
Reasoning
QW
Qwen3 Coder Next Opus 4.6 Reasoning Distilled
Qwen · samuelcardillo
Params80B
Context256K
Q4_K_M48.5 GB
CodingReasoning
QW
Qwen3.8 27B Cold Fusion GAIN V1.1 NM DAU NEO MAX MTP
Qwen · fribourgquants
Params26.9B
Context256K
Q4_K_M18.0 GB
CodingReasoningRoleplay
QW
Qwen3.5 9B Cyberpunk2077 Xiaotian Qin V2 V3 5pass
Qwen · mradermacher
Params9.2B
Context256K
Q4_K_M5.8 GB
ReasoningTool use
DE
DeepSeek R1 Distill Qwen 1.5B
DeepSeek · mradermacher
Params1.78B
Context128K
Q4_K_M1.1 GB
Reasoning
QW
SpaceThinker Qwen2.5VL 3B
Qwen · remyxai
Params3.09B
Context125K
Q4_K_M1.9 GB
ReasoningVision
QW
JoyFox Reverie 27B
Qwen · joyfox
Params27.3B
Context256K
Q4_K_M16.5 GB
ReasoningRoleplayTool use
GE
Gemma 4 12B It Esper4
Gemma · mradermacher
Params11.9B
Context256K
Q4_K_M7.4 GB
CodingReasoning
LF
Koda IDS Frontier F16
Lfm · netgoat-ai
Params2.7B
Context128K
Q4_K_M1.7 GB
Reasoning
QW
Qween3 4B deepthinking finetune
Qween · dilipnswamy
Params4.02B
Context256K
Q4_K_M2.5 GB
ReasoningTool use
GE
Gemma 4 26B A4B It Uncensored MAX
Gemma · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
Reasoning
LL
HexaMind Llama 3.1 8B v25 Generalist
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
Reasoning
GE
Gemma 4 31B It Uncensored MAX
Gemma · prithivMLmods
Params30.7B
Context256K
Smallest32.6 GB
ReasoningVision
GE
Gemma4 12B Uncensored
Gemma · mradermacher
Params11.9B
Context256K
Q4_K_M7.4 GB
ReasoningTool useVision
GE
gemma 4 E4B Agentic Opus Reasoning GeminiCLI
Gemma · deadbydawn101
Params7.5B
Context128K
Q4_K_M5.3 GB
CodingReasoningTool use
GE
BugTraceAI Apex G4 26B Q4
Gemma · BugTraceAI
Params25.2B
Context256K
Smallest16.8 GB
ReasoningTool use
DE
Qwen3 14B DeepSeek v3.2 Speciale Distill
DeepSeek · TeichAI
Params14.8B
Context40K
Q4_K_M9.0 GB
CodingReasoning
QW
Qwen3.5 40B Holodeck Claude Deckard Picard Heretic
Qwen · mradermacher
Params39.1B
Context256K
Q4_K_M23.9 GB
CodingReasoningRoleplay
QW
Qwen3.5 9B Abliterated v2 MAX
Qwen · prithivMLmods
Params8.95B
Context256K
Smallest9.5 GB
ReasoningVision

Other uses

Keep browsing