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 VL 4B Thinking
Qwen · bartowski
Params4B
Context256K
Q4_K_M2.5 GB
ReasoningVision
NE
AceReason Nemotron 7B
Nemotron · bartowski
Params7.62B
Context128K
Q4_K_M4.7 GB
CodingReasoningTool use
GL
LFM2 8B A1B GLM 4.7 Flash Thinking Quantum IQ1C P
GLM · mradermacher
Params8.34B
Context125K
Q4_K_M5.0 GB
CodingReasoningRoleplay
RI
Ring Mini 2.0
Ring · mradermacher
Params16.3B
Context32K
Q4_K_M9.9 GB
Reasoning
QW
Qwen3 ST The Next Generation II v1 256k Ctx 6B
Qwen · mradermacher
Params6.33B
Context256K
Q4_K_M3.9 GB
CodingReasoningTool use
QW
Whittle Qwen 3.8 35B A3B
Qwen · mradermacher
Params35.5B
Context256K
Q4_K_M21.3 GB
CodingReasoning
BL
G2 9B Blackout R1
Blackout · bartowski
Params9.24B
Context8K
Q4_K_M5.8 GB
Reasoning
HO
Holo3 35B A3B
Holo · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool useVision
LF
LFM2.5 24B A2B Uncensored2
Lfm · mradermacher
Params24B
Context128K
Q4_K_M14.5 GB
ReasoningTool use
QW
Qwen3 24B A4B Freedom HQ Thinking Abliterated Heretic NEOMAX Imatrix
Qwen · DavidAU
Params17.9B
Context256K
Q4_K_M11.3 GB
ReasoningRoleplay
LL
Llama 3 JPRP NSFW 8B
Llama · mradermacher
Params8B
Context8K
Q4_K_M4.9 GB
ReasoningRoleplay
QW
VeriReason Qwen2.5 7b RTLCoder Verilog GRPO Reasoning Tb
Qwen · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
CodingReasoningTool use
GE
Gemma 3 1B It GLM 4.7 Flash Heretic Uncensored Thinking
Gemma · mradermacher
Params1B
Context32K
Q4_K_M0.8 GB
Reasoning
QW
GeoLLM Qwen3.5 27B
Qwen · mradermacher
Params26.9B
Context256K
Q4_K_M16.5 GB
ReasoningTool use
NE
NVIDIA Nemotron 3.5 Super VL 120B A12B NVFP4 LiLiCorr
Nemotron · magnitudedev
Params1.66B
Context1024K
Smallest1.4 GB
ReasoningTool useVision
DE
Deepseek-R1-0528-Qwen3-8B
DeepSeek · cecloud33
Params8.19B
Context128K
Q4_K_M5.0 GB
ReasoningTool use
QW
Qwen3.5-4B-Abliterated-Claude-4.6-Opus-Reasoning-Distilled
Qwen · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool useVision
QW
Qwen3 53B A3B 2507 TOTAL RECALL v2 MASTER CODER
Qwen · mradermacher
Params53B
Context256K
Q4_K_M32.1 GB
CodingReasoningTool use
AZ
Aztec Coder 4B
Aztec · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
CodingReasoningTool use
CA
CantoneseLLM v2.0 30B A3B Thinking
Cantonesellm · mradermacher
Params30.5B
Context40K
Q4_K_M18.6 GB
Reasoning
QW
Diffusion Qwen3.5 4B
Qwen · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool use
QW
Qwen3.8 27B TURBO Fable Cold Fusion 735 882 Heretic Uncensored NEO CODER MAX MTP
Qwen · Sameer3336s
Params26.9B
Context256K
Q4_K_M18.0 GB
CodingReasoningRoleplay
MI
MiniCPM5 2B Heretic Abliterated
MiniCPM · mradermacher
Params2.52B
Context128K
Q4_K_M1.6 GB
CodingReasoningTool use
QW
shisa v2.1 qwen3 8b i1
Qwen · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
UW
UwU 14B Math v0.2 i1
Uwu · mradermacher
Params14.8B
Context128K
Q4_K_M9.0 GB
Reasoning
QW
Qwen3.5 2B Uncensored Zero Refusal
Qwen · AkaumiKaede
Params1.88B
Context256K
Q4_K_M1.3 GB
ReasoningRoleplayTool use
OM
Omni R1 Zero
Omni · mradermacher
Params7.01B
Context10K
Q4_K_M4.3 GB
Reasoning
MI
Huihui Ministral 3 3B Reasoning 2512 Abliterated
Mistral · mradermacher
Params3.43B
Context256K
Q4_K_M2.1 GB
Reasoning
QW
Qwen_Qwen3 VL 30B A3B Thinking
Qwen · lmstudio-community
Params30.5B
Context256K
Q4_K_M18.6 GB
ReasoningTool useVision
GE
Gemma 4 26B A4B It Heretic Antislop
Gemma · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
ReasoningTool use

Other uses

Keep browsing