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
mango qwen27 orca bf16
Qwen · isilicon
Params27.3B
Context256K
Smallest54.7 GB
ReasoningTool use
GE
gemma 4 12B it QUASAR Q4 0
Gemma · QUASAR-QAT
Params11.9B
Context256K
Smallest7.0 GB
ReasoningTool useVision
GL
GLM 5.3 Flash
GLM · muterornament
Params321B
Context1024K
Smallest93.1 GB
ReasoningTool useVision
NE
Nemotron Terminal 14B Heretic
Nemotron · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
CodingReasoningTool use
QW
Qwen3.8 27B Uncensored IQ4 XS MTP 16GB VRAM
Qwen · Suseezz
Params27.3B
Context256K
Smallest13.9 GB
ReasoningTool use
QW
mango qwen35 122b q4
Qwen · isilicon
Params122B
Context256K
Smallest74.2 GB
ReasoningTool use
KV
Kvark Sparkle 1.0 27B
Kvark · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
CodingReasoningTool use
MO
PanShi Audit1.0 12B
Moon · mradermacher
Params11.9B
Context256K
Q4_K_M7.4 GB
ReasoningTool useVision
AG
AgentHorse 4B 1.0
Agents · CloudGoat
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool useVision
KE
Kepler Reasoning 7B
Kepler · mradermacher
Params7.61B
Context32K
Q4_K_M4.7 GB
CodingReasoningTool use
QW
Qwen3.5 9B Heretic
Qwen · SassyDiffusion
Params8.95B
Context256K
Q4_K_M5.8 GB
ReasoningTool useVision
GE
Gemma4 12B IT Abliterated
Gemma · mradermacher
Params11.9B
Context128K
Q4_K_M7.4 GB
ReasoningTool use
FR
Froopert 31B
Froopert · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
ReasoningRoleplayTool use
XI
Xing4.0 29B Intent
Xing · XingChen-AGI
Params31.2B
Context256K
Smallest17.8 GB
ReasoningTool use
QW
Qwen3.8 27B Uncensored
Qwen · rax4901
Params27.3B
Context256K
Q4_K_M16.5 GB
ReasoningTool useVision
QW
Qwen3.6 35B A3B Abliterated MAX
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningVision
QW
Qwen3.6 27B Heretic2 Uncensored Finetune Thinking
Qwen · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
ReasoningRoleplay
QW
Qwen3 VL 8B Thinking Abliterated
Qwen · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
ReasoningTool useVision
MU
Muse Glimmer 30B SOMPOA Heresy
Muse · mradermacher
Params27.9B
Context128K
Q4_K_M16.9 GB
ReasoningTool useVision
ME
Hy Memory 30B A3B
Memory · abenzerps
Params30.1B
Context256K
Q4_K_M18.2 GB
ReasoningTool use
QW
Rombo LLM V3.0 Qwen 72b
Qwen · bartowski
Params72.7B
Context32K
Q4_K_M47.4 GB
ReasoningTool use
DO
DocWain 14B v2 Unified
Docwain · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
ReasoningTool use
ST
StagAI CyberSecurity 26B A4B v2 VLM GGUF BF16
Stagai · deer-sec
Params25.2B
Context256K
Smallest50.5 GB
ReasoningTool useVision
ST
G4 31B Style r1 DPO c30
Style · ApocalypseParty
Params30.7B
Context256K
Q4_K_M18.7 GB
ReasoningTool use
QI
Qianfan-OCR
Qianfan · Mungert
Params4.42B
Context32K
Q4_K_M3.1 GB
ReasoningVision
SA
TheSkullery L3.3 exp unnamed model 70b v0.5
San · bartowski
Params70.6B
Context128K
Q4_K_M42.5 GB
Reasoning
QW
Qwen3.8 27B ColdFusion GAIN Blackwell DFlash2 Ultra V1.0
Qwen · ToBeStyled
Params27.3B
Context256K
Q4_K_M1.1 GB
ReasoningVision
OR
Ornith 1.5 35B A3B Heretic Ja
Ornith · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
ReasoningTool useVision
QW
CriticLeanGPT Qwen3 14B RL
Qwen · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
ReasoningTool use
DA
Dark Scarlett 27B v3.0
Dark · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
ReasoningRoleplayTool use

Other uses

Keep browsing