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.
QW
Qwen3.5 4B Neo
Qwen · Jackrong
Params4.21B
Context256K
Q4_K_M2.7 GB
PA
Palette RP 9B 2609 v0.05
Palette · mradermacher
Params9.2B
Context256K
Q4_K_M5.8 GB
QW
Qwen3 16B A3B Abliterated
Qwen · mradermacher
Params16B
Context40K
Q4_K_M9.8 GB
GE
Gemma 4 12B It
Gemma · mradermacher
Params11.9B
Context256K
Q4_K_M7.4 GB
QW
Huihui Qwen3.8 27B Abliterated
Qwen · mitkox
Params27.3B
Context256K
Q4_K_M16.8 GB
HU
HuatuoGPT O1 8B
Huatuogpt · bartowski
Params8B
Context128K
Q4_K_M4.9 GB
LL
Codepy Deepthink 3B
Llama · QuantFactory
Params3.61B
Context128K
Q4_K_M2.2 GB
QW
Qwen3 4B Thinking heretic
Qwen · saidutta69
Params4.02B
Context256K
Q4_K_M2.5 GB
GL
GLM 4.7 Flash Impotent Heresy
GLM · mradermacher
Params29.9B
Context198K
Q4_K_M18.1 GB
QW
Qwen3 4B Thinking MiniMax M2.1 Coder
Qwen · TeichAI
Params4.02B
Context256K
Q4_K_M2.5 GB
GE
Gemma 4 26B A4B Abliterated
Gemma · DuoNeural
Params25.2B
Context256K
Smallest13.3 GB
DA
Dark Scarlett v1.0 35B A3B
Dark · ReadyArt
Params35.5B
Context256K
Q4_K_M22.9 GB
NE
Nex-N2.5-mini
Nex · vultr
Params34.7B
Context256K
Q4_K_M23.3 GB
MU
Muse Glimmer 30B Esper4
Muse · mradermacher
Params27.9B
Context128K
Q4_K_M16.9 GB
DE
Deepseek R1 1.5B KomorAI
DeepSeek · KomorAI
Params1.78B
Context128K
Q4_K_M1.1 GB
GO
Google_Medgemma 1.5 4b It
Google · Bercraft
Params3.88B
Context128K
Q4_K_M2.5 GB
JU
Jupiter G 8B
Jupiter · mradermacher
Params7.52B
Context128K
Q4_K_M5.3 GB
GE
Gemma 4 Dark Orthia 31B
Gemma · mradermacher
Params32.1B
Context256K
Q4_K_M19.5 GB
MI
Mistral Nemo Instruct 2407 12B Thinking HI Claude Opus High Reasoning
Mistral · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
QW
Qwen3.8 27B Uncensored Aggressive
Qwen · philbert440
Params26.9B
Context256K
Q4_K_M19.0 GB
LF
LFM2.5 230M heretic
Lfm · saidutta69
Params230M
Context125K
Q4_K_M0.2 GB
SP
Spark X2.6 1.7B
Spark · mradermacher
Params1.71B
Context1024K
Q4_K_M1.1 GB
DE
Delphermes 8B
Delphermes · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
GO
Godoter 27B
Godoter · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
ME
Melinoe Next 80B A3B Thinking Diluted v0
Melinoe · mradermacher
Params79.7B
Context256K
Q4_K_M48.4 GB
QW
Merkyor/Qwen3.8-27B-Coder390-EfficientThink
Qwen · gsdavidp
Params27.3B
Context256K
Smallest3.2 GB
GL
LFM2 8B A1B GLM 4.7 Flash Thinking Quantum IQ1C
GLM · mradermacher
Params8.34B
Context125K
Q4_K_M5.0 GB
QW
Qwen3 14B Awq Compatible Instruct
Qwen · 1bit-MONSTER
Params14.8B
Context40K
Q4_K_M9.0 GB
QW
Qwen3.5 35B A3B
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
AL
G4 Alice v1.1 31B
Alice · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB