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
GE
Gemma 3 12b It Vl Polaris GLM 4.7 Flash VAR Thinking Instruct Heretic Uncensored
Gemma · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
ReasoningVision
QW
Qwen3.5 9B GLM Wannabe
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool use
QW
Qwen3.8 27B Abliterated
Qwen · Grimxlock
Params26.9B
Context256K
Q4_K_M16.5 GB
ReasoningTool useVision
QW
Qwen3 ST The Next Generation II E32 v1 256k Ctx 6B
Qwen · mradermacher
Params6.33B
Context256K
Q4_K_M3.9 GB
CodingReasoning
OR
Ornith 1.5 9B OBLITERATED
Ornith · mradermacher
Params9.2B
Context256K
Q4_K_M5.8 GB
ReasoningTool use
RU
RusMind 4.5 Momentum
Rusmind · DICPlay
Params4.65B
Context128K
Smallest9.3 GB
ReasoningTool use
QW
Qwopus3.6 27B Coder Templatefix HF
Qwopus · Jackrong
Params27B
Context256K
Q4_K_M16.5 GB
CodingReasoningTool use
QW
Qwen3.8-27b-Terse-Coder
Qwen · Shockem
Params27.3B
Context256K
Q4_K_M16.8 GB
CodingReasoningVision
QW
Qwen3.5 4B Element
Qwen · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningRoleplayTool use
LF
LFM2.5-24B-A2B
Lfm · IsValorum
Params24B
Context128K
Smallest8.2 GB
ReasoningTool use
DE
Deepthink Reasoning 7B imatrix
Deepthink · duyntnet
Params7.62B
Context32K
Q4_K_M4.7 GB
ReasoningTool use
LF
LFM3 1.7B abliterated
Lfm · bowtiedrahman
Params1.73B
Context256K
Q4_K_M1.1 GB
CodingReasoningTool use
QW
Qwopus3.5 9B v3.5
Qwopus · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool use
QW
Qwythos 9B Claude Mythos 5 1M MTP
Qwythos · mradermacher
Params9.2B
Context1024K
Q4_K_M5.8 GB
ReasoningTool useVision
OM
OmniCoder 2 9B
Omnicoder · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
CodingReasoningTool use
MI
Ministral 3 8B Claude Opus Reasoning Distilled
Mistral · xtools-at
Params8.49B
Context256K
Q4_K_M5.2 GB
ReasoningTool useVision
ME
Mellum2.1 12B A2.5B Thinking Abliterated
Mellum · mradermacher
Params12.1B
Context128K
Q4_K_M8.1 GB
ReasoningTool use
AT
ATLAS Teach 8B Instruct
Atlas · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
OL
Olmo-3-7B-Think
OLMo · Mungert
Params7.3B
Context64K
Q4_K_M4.7 GB
Reasoning
MO
Mordant 7B Think
Mordant · mradermacher
Params7.3B
Context64K
Q4_K_M4.5 GB
Reasoning
GE
Gemma 4 E2B It The DECKARD Expresso ONE Universe HERETIC UNCENSORED Thinking
Gemma · mradermacher
Params4.65B
Context128K
Q4_K_M3.4 GB
CodingReasoningRoleplay
MI
MiniCPM V 4.7 1B DSpark
MiniCPM · magnitudedev
Params214M
Context256K
Smallest0.2 GB
ReasoningTool useVision
QW
Qwen3.5 122B A10B Heretic v2
Qwen · mradermacher
Params122B
Context256K
Q4_K_M74.2 GB
ReasoningTool useVision
MI
Mini Hydra
Mini · mradermacher
Params30.5B
Context40K
Q4_K_M18.6 GB
ReasoningTool use
DA
Darwin 36B Opus
Darwin · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
Reasoning
OR
Ornstein 27B SABER
Ornstein · mradermacher
Params26.9B
Context256K
Q4_K_M16.5 GB
ReasoningTool use
KE
Kestrel 4B Coder
Kestrel · mradermacher
Params4.33B
Context256K
Q4_K_M2.8 GB
CodingReasoningTool use
BO
Boulesis 26B A4B
Boulesis · mradermacher
Params26B
Context256K
Q4_K_M17.2 GB
ReasoningRoleplay
XO
XORTRON.CriminalComputing.2026.4B.Instruct.NEXT
Xortron · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool useVision
RU
RusMind 4.5.1 Momentum
Rusmind · DICPlay
Params4.65B
Context128K
Smallest9.3 GB
ReasoningTool use

Other uses

Keep browsing