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 4B Instruct 2507 heretic
Qwen · saidutta69
Params4B
Context256K
Q4_K_M2.5 GB
SP
Spark X2.6 4B
Spark · prithivMLmods
Params4.11B
Context1024K
Q4_K_M2.6 GB
NU
Nuqta Arabic OCR 4B
Nuqta · SalahALHaismawi
Params4.54B
Context256K
Q4_K_M2.9 GB
GE
Gemma 4 12B It Guardpoint
Gemma · mradermacher
Params11.9B
Context256K
Q4_K_M7.4 GB
UT
UtevoLux 3.6 27B
Utevolux · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
LL
Fireball Alpaca Llama3.1.08 8B Philos C R1 i1
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
LL
Llama3.1 MOE 4X8B Gated IQ Multi Tier Deep Reasoning 32B
Llama · mradermacher
Params24.9B
Context128K
Q4_K_M15.2 GB
FA
Faithful_Thinking_with_Image
Faithful · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
HE
Hermes 4 14B
Hermes · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
AR
AREX Base
Arex · bartowski
Params122B
Context256K
Q4_K_M74.9 GB
GE
Gemma 4 12B OBLITERATED
Gemma · mradermacher
Params11.9B
Context128K
Q4_K_M7.4 GB
GE
Gemma 4 E2B It Anon Reasoning
Gemma · mradermacher
Params4.65B
Context128K
Q4_K_M3.4 GB
QW
Qwen3 4B Abliterated TIES
Qwen · mradermacher
Params4.02B
Context32K
Q4_K_M2.5 GB
QW
Qwen3.5 13B Deckard Heretic Uncensored Thinking
Qwen · mradermacher
Params12.4B
Context256K
Q4_K_M7.7 GB
BE
Beam 1.0 501B A23B
Beam · bartowski
Params501B
Context1024K
Q4_K_M314.5 GB
HU
Huihui Qwythos 9B Claude Mythos 5 1M Abliterated
Huihui · Abiray
Params9.2B
Context1024K
Q4_K_M5.8 GB
QW
reasoning summarizer qwen3.5 0.8b preview
Qwen · mithulaartigala
Params752M
Context256K
Q4_K_M0.5 GB
KL
Klyrune 2B Coder
Klyrune · mradermacher
Params2.52B
Context128K
Q4_K_M1.6 GB
IQ
IQuest Coder V1 40B Thinking Heretic
Iquest · mradermacher
Params39.8B
Context128K
Q4_K_M24.0 GB
QW
Qwen3.5 9B Uncensored Cyber v3
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
QW
qwen36 35b a3b distill
Qwen · freakyskittle
Params35.5B
Context256K
Q4_K_M21.7 GB
KI
Kiwen1.1 27B
Kiwen · bartowski
Params27.3B
Context256K
Q4_K_M17.8 GB
AZ
Aztec Coder 4B
Aztec · prithivMLmods
Params4.21B
Context256K
Q4_K_M2.7 GB
QW
Qwen3 Stargate SG1 Uncensored Abliterated 8B
Qwen · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
ZE
zen 4b i1
Zen · mradermacher
Params4.02B
Context32K
Q4_K_M2.5 GB
MO
Moe 4x7b reason code qa i1
Moe · mradermacher
Params24.2B
Context32K
Q4_K_M14.6 GB
QW
Qwen3.6 35B A3B heretic MTP IQ4 XS
Qwen · hermeticvm
Params35.5B
Context256K
Smallest19.2 GB
QW
Qwen3.5 40B Holodeck Claude Deckard Picard Heretic
Qwen · mradermacher
Params39.1B
Context256K
Q4_K_M23.9 GB
LL
Deep Reasoning Llama 3.2 Dolphin3.0 3B i1
Llama · mradermacher
Params3.21B
Context128K
Q4_K_M2.0 GB
QW
Nemotron Research Reasoning Qwen 1.5B
Qwen · bartowski
Params1.78B
Context128K
Q4_K_M1.1 GB