Q4_K_M GGUF models

4-bit k-quant, medium. The common default: a good balance of size and quality. 148631 models have a Q4_K_M file. Sizes run from 1M to 2450B parameters. The longest trained context is 4194304K tokens.

Most downloadedNewestLargestLongest contextSmallest
OR
Ornith-1.5-35B
Ornith · na0x2c6
Params35.5B
Context256K
Q4_K_M21.7 GB
GGUF
GD
GDP 4B
Gdp · mradermacher
Params4.02B
Context256K
Q4_K_M2.5 GB
ReasoningTool useVision
LL
Llm Jp 4.1 32b A3B Thinking
Llm · OS-Software
Params32B
Context64K
Q4_K_M21.5 GB
Reasoning
DE
DeepSeek R1 Distill Qwen 7B
DeepSeek · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
Reasoning
FA
FastH3 Omni GGUFs
Fastvideo · realrebelai
Params22.1B
Context—
Q4_K_M13.8 GB
GGUF
HO
K2 Horizon 32B Heretic
Horizon · mradermacher
Params34.8B
Context512K
Q4_K_M21.1 GB
Coding
YI
ChatAllInOne-Yi-34B-200K-V1
Yi · mradermacher
Params34.4B
Context195K
Q4_K_M20.7 GB
GGUF
QW
Qwen3.8 Flash Next FP8 Abliterated
Qwen · GCSA-AiLab
Params177B
Context256K
Q4_K_M2.8 GB
Vision
GE
gemma-1.1-7b-it
Gemma · bartowski
Params8.54B
Context8K
Q4_K_M5.3 GB
GGUF
AI
Airoboros L2 70B 2.1
Airoboros · TheBloke
Params69B
Context4K
Q4_K_M41.4 GB
GGUF
FL
Sakura FLUX.3 Image Klein
Flux · webmp3
Params5.55B
Context—
Q4_K_M3.3 GB
GGUF
JA
stabilityai_japanese-stablelm-instruct-gamma-7b
Japanese · TheBloke
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
QW
silicon based girlfriend v2
Qwen · RX5950XT
Params9.2B
Context256K
Q4_K_M5.8 GB
RoleplayVision
KR
krea2 turbo uncensored v1.1 BACKUP
Krea · Quiho
Params12.8B
Context—
Q4_K_M7.2 GB
GGUF
QW
Qwen3.8 27B uncensored
Qwen · ressl
Params27.3B
Context256K
Q4_K_M16.8 GB
Vision
SA
Sage A1.5
Sage · mradermacher
Params35.5B
Context256K
Q4_K_M21.7 GB
CodingTool useVision
GL
Glistening Gem 31B v2.1
Glistening · bartowski
Params30.7B
Context256K
Q4_K_M19.6 GB
Vision
CO
Yi Coder 9B Chat
Coder · mradermacher
Params8.83B
Context128K
Q4_K_M5.3 GB
Coding
GL
Glm 4 9b Chat
GLM · bartowski
Params9.4B
Context128K
Q4_K_M6.3 GB
GGUF
LU
G4 LuneLight 31B
Lunelight · zerofata
Params30.7B
Context256K
Q4_K_M18.7 GB
ReasoningTool use
QW
Qwen2.5 7B Instruct 1M
Qwen · bartowski
Params7.62B
Context986K
Q4_K_M4.7 GB
GGUF
GR
Granite-4.1-3B
Granite · unsloth
Params3.4B
Context128K
Q4_K_M2.1 GB
GGUF
QW
Darrellbest Qwen Image 2.1 PE I2I Heretic
Qwen · darrellbest
Params8.95B
Context256K
Q4_K_M5.6 GB
Vision
SH
Shadow Siren 14B Pruned
Shadow · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
Roleplay
MI
llava 1.6 mistral 7b
Mistral · cjpais
Params7.24B
Context32K
Q4_K_M4.4 GB
Vision
QW
Huihui Qwen3.5 4B Abliterated
Qwen · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
GGUF
GE
Wanabi Gemma4 31B
Gemma · kawaimasa
Params30.7B
Context256K
Q4_K_M18.7 GB
Vision
YA
YandexGPT 5 Lite 8B Instruct
Yandexgpt · yandex
Params8B
Context32K
Q4_K_M4.9 GB
GGUF
QW
Qwen3.8 Flash Next
Qwen · FINAL-Bench
Params177B
Context256K
Q4_K_M100.2 GB
GGUF
WH
whiterabbitneo_whiterabbitneo-33b-v1
Whiterabbitneo · TheBloke
Params33.3B
Context16K
Q4_K_M19.9 GB
GGUF

Other quants

Keep browsing