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 40B RoughHouse Claude 4.6 Opus Polar Deckard Uncensored Heretic Thinking
Qwen · mradermacher
Params39.1B
Context256K
Q4_K_M23.9 GB
VE
Veritas 12B
Veritas · bartowski
Params11.8B
Context128K
Q4_K_M7.3 GB
DE
DeepSeek R1 Distill Qwen 7B Uncensored
DeepSeek · Andycurrent
Params1.78B
Context128K
Q4_K_M1.1 GB
MI
Magistral Small 2506
Mistral · mradermacher
Params23.6B
Context40K
Q4_K_M14.3 GB
QW
Qwen3.8-27B
Qwen · emee-ai
Params27.3B
Context256K
Q4_K_M16.5 GB
QW
Qwen_Qwen3 4B
Qwen · Alcoft
Params4.02B
Context40K
Q4_K_M2.5 GB
HU
Huihui MiroThinker v1.5 30B Abliterated
Huihui · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
QW
Qwen3Guard Gen 4B
Qwen · mradermacher
Params4.41B
Context32K
Q4_K_M2.7 GB
MI
MiniCPM5 2B
MiniCPM · mradermacher
Params2.52B
Context128K
Q4_K_M1.6 GB
SO
Solar Decision JEV 27B VL
Solar · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
LL
Llama 3.1 Storm 8B
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
GL
GLM-5.3-Flash
GLM · 6block
Params313B
Context1024K
Smallest70.7 GB
QW
Qwen3.8 27B TURBO Fable Cold Fusion 735 882 Heretic Uncensored NEO CODER MAX MTP
Qwen · fribourgquants
Params26.9B
Context256K
Q4_K_M18.0 GB
QW
Swift 1.5 Qwen3.8 Flash Next MTP for GGUF and NVFP4
Qwen · adriandj3
Params2.61B
Context256K
Smallest2.8 GB
GR
Grug 3b
Grug · bartowski
Params4.17B
Context256K
Q4_K_M2.7 GB
CO
CodeScout 14B
Codescout · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
EL
ELYZA Thinking 1.0 llm jp 4 33b
Elyza · mmnga-o
Params33.2B
Context64K
Q4_K_M20.2 GB
QW
Qwen3.5 9B Abliterated v2 MAX
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
FL
Q3.5 9B DS v4 Flash DA
Flash · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
DE
DeepSeek V4 Flash
DeepSeek · persadian
Params229B
Context1024K
Smallest61.5 GB
FO
FoundRoot 14B
Foundroot · mradermacher
Params14.8B
Context128K
Q4_K_M9.0 GB
DE
Huihui ai.DeepSeek R1 Distill Qwen 7B Abliterated
DeepSeek · DevQuasar-7
Params7.62B
Context128K
Q4_K_M4.7 GB
QW
ThinkingCap Qwen3.8 27B Uncensored Heretic
Qwen · OS-Software
Params27B
Context256K
Q4_K_M16.5 GB
QW
NOESIS Qwopus3.5 9B Translate v3.5 BF16
Qwopus · AMAImedia
Params8.95B
Context256K
Smallest2.9 GB
QW
Qwen3 VL 8B Thinking Abliterated
Qwen · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
EL
ELYZA Thinking 1.0 llm jp 4 32b a3b
Elyza · mmnga-o
Params32.1B
Context64K
Q4_K_M21.4 GB
ZA
Zawen v0.1 35B A3B
Zawen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
TE
Ternary Bonsai 2 27B Abliterated v2 PQ2 0 MTP
Ternary · timfromhcs
Params27B
Context256K
Smallest7.2 GB
SM
SMOLM2Prover
SmolLM · reaperdoesntknow
Params362M
Context8K
Q4_K_M0.3 GB
QI
Qianfan OCR
Qianfan · ggml-org
Params4.42B
Context32K
Smallest4.7 GB