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
Qwen3.5 9B The Defiant Fable Uncensored Heretic NEO IMATRIX MAX MTP
Qwen · DavidAU
Params8.95B
Context256K
Q4_K_M6.8 GB
CodingReasoningRoleplay
QW
Qwen3.8 27B TURBO Fable Cold Fusion 735 882 Heretic Uncensored NEO CODER MAX MTP
Qwen · DavidAU
Params27B
Context256K
Q4_K_M18.0 GB
CodingReasoningRoleplay
QW
Swift 1.5 Qwen3.8 27B GSQ RCO
Qwen · ukisai
Params27B
Context—
Smallest0.0 GB
Reasoning
QW
Qwen3.8 35B A3B Distill
Qwen · empero-ai
Params35.5B
Context256K
Q4_K_M21.7 GB
ReasoningVision
QW
Qwen3.8 Flash Next Uncensored
Qwen · orcarouter
Params177B
Context256K
Q4_K_M119.2 GB
ReasoningTool useVision
QW
Qwopus3.8 27B Flash V2
Qwopus · Jackrong
Params28B
Context256K
Q4_K_M16.8 GB
CodingReasoningTool use
QW
ThinkingCap Qwen3.8 27B
Qwen · bottlecapai
Params27.3B
Context256K
Q4_K_M17.4 GB
ReasoningVision
HU
Cyber Tiel Coder 35B A3B GGUF MTP
Huihui · peculiar-ragdoll
Params35.5B
Context256K
Q4_K_M22.5 GB
CodingReasoningTool use
QW
Qwen3.8-27B
Qwen · agentionai
Params27.3B
Context256K
Q4_K_M16.5 GB
ReasoningTool useVision
CY
Cyber Ornith 1.5 9B OBLITERATED
Cyber · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
CodingReasoningTool use
SP
Sharp Spark X2.5 4B
Spark · peculiar-ragdoll
Params4.11B
Context—
Smallest0.0 GB
Reasoning
QW
Swift 1.5 Qwen3.8 Flash Next GSQ RCO
Qwen · ukisai
Params177B
Context—
Smallest0.6 GB
ReasoningVision
IN
Inkling-Small
Inkling · unsloth
Params264B
Context1024K
Q4_K_M162.5 GB
ReasoningVision
QW
Swift 1.5 Qwen3.8 27B heretic GSQ RCO
Qwen · jegreene
Params27.3B
Context256K
Smallest9.6 GB
ReasoningTool useVision
QW
Qwen3.8 27B
Qwen · DavidAU
Params27B
Context256K
Q4_K_M16.5 GB
CodingReasoningVision
QW
Qwen3.8 4B
Qwen · empero-ai
Params4.33B
Context256K
Q4_K_M2.8 GB
Reasoning
QW
Qwen3.8 27B Coder390 EfficientThink Opus5.5 GPT6Astra Grok4.7 DSV4Pro K3 SFT RLOO MTP DFlash2
Qwen · nerkyor
Params27.3B
Context256K
Smallest3.2 GB
CodingReasoningTool use
QW
Swift Qwen3.8 27b
Qwen · ukisai
Params27.3B
Context256K
Q4_K_M18.0 GB
ReasoningVision
QW
Qwen3.8 9B
Qwen · empero-ai
Params9.2B
Context256K
Q4_K_M5.8 GB
Reasoning
QW
Qwen3.8 Flash Next Gyro
Qwen · agentionai
Params177B
Context256K
Smallest2.7 GB
ReasoningTool useVision
QW
Qwen3.8 Flash Next
Qwen · AtomicChat
Params177B
Context256K
Q4_K_M94.5 GB
ReasoningTool useVision
QW
Qwen3.6 35B A3B Uncensored Genesis Hermes
Qwen · LuffyTheFox
Params34.7B
Context256K
Smallest20.2 GB
ReasoningTool useVision
QW
Qwen3.8 2B
Qwen · empero-ai
Params1.94B
Context256K
Q4_K_M1.3 GB
Reasoning
QW
Qwen3.8 27B Fable 5 Coding Distilled
Qwen · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
ReasoningVision
QW
Qwen3.6 27B Fable Fusion 711 Uncensored Heretic NM DAU NEO MAX MTP
Qwen · DavidAU
Params27B
Context256K
Q4_K_M18.0 GB
CodingReasoningRoleplay
QW
Qwen3.8 Flash Next Gyro abliterated Huihui
Qwen · agentionai
Params177B
Context256K
Smallest2.7 GB
ReasoningTool useVision
QW
Qwen3.5 9B Kimi K3 Distilled
Qwen · mradermacher
Params9.2B
Context256K
Q4_K_M5.8 GB
ReasoningVision
B1
B1 9B
mradermacher
Params9.2B
Context256K
Q4_K_M5.8 GB
ReasoningTool useVision
TE
Tess 4 27B
Tess · migtissera
Params27B
Context256K
Q4_K_M2.0 GB
ReasoningVision
QW
Qwythos-9B-v2
Qwythos · empero-ai
Params8.95B
Context1024K
Q4_K_M5.7 GB
ReasoningTool useVision

About Reasoning GGUF models

46,569 GGUF models are filed under Reasoning: models that think step by step before answering. The most downloaded are Qwen3.5 9B The Defiant Fable Uncensored Heretic NEO IMATRIX MAX MTP, Qwen3.8 27B TURBO Fable Cold Fusion 735 882 Heretic Uncensored NEO CODER MAX MTP and Swift 1.5 Qwen3.8 27B GSQ RCO. Parameter counts run from 1M to 5376B, and the longest trained context window is 5120K tokens.

Reasoning models write long chains of thought before the answer, so a larger context window and faster generation matter more than usual. The families you will see most are Qwen (17571), Gemma (3426) and DeepSeek (2899).

Frequently asked questions

What are Reasoning GGUF models?

Models that think step by step before answering. There are 46,569 of them on this site.

Which Reasoning GGUF model should I start with?

The most downloaded is Qwen3.5 9B The Defiant Fable Uncensored Heretic NEO IMATRIX MAX MTP. Choose the size that fits your GPU, then a Q4_K_M quant unless you have memory to spare.

Other uses

Keep browsing