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
QW
Qwen3.6 12B IQ Ultra Heretic Uncensored Thinking V2 Hightop
Qwen · KevinJK51
Params11.7B
Context256K
Q4_K_M7.3 GB
Reasoning
ST
Step-3.7-Flash
Step · unsloth
Params197B
Context256K
Q4_K_M122.1 GB
Vision
QW
Qwen3.8 27B Uncensored
Qwen · xCloudinfo
Params26.9B
Context256K
Q4_K_M16.5 GB
ReasoningTool useVision
LA
latxa-7b-v1.2
Latxa · mradermacher
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
GE
gemma 4 E4B it heretic
Gemma · Abiray
Params7.5B
Context128K
Q4_K_M5.3 GB
CodingVision
AP
APUS Reflex 9B
Apus · apus-ailab
Params8.95B
Context256K
Q4_K_M5.6 GB
GGUF
MI
mistralai_mistral-7b-v0.1
Mistral · TheBloke
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
GE
Gemma 4 31B Fable Coder
Gemma · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
CodingTool useVision
MI
Mistral Nemo Instruct 2407 12B Thinking M Claude Opus High Reasoning
Mistral · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
ReasoningRoleplay
GR
TwIL LM3 Pro
Granite · webAI-Official
Params3.66B
Context128K
Q4_K_M2.2 GB
ReasoningTool use
SO
Sommerfugl 31b v2
Sommerfugl · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
GGUF
HE
Hemmingway 1
Hemmingway · botp
Params27.3B
Context256K
Q4_K_M17.4 GB
ReasoningTool use
QW
Qwen1.5-0.5B-Chat-AWQ-fp16
Qwen · Qwen
Params620M
Context32K
Q4_K_M0.4 GB
GGUF
HU
HunyuanOCR
Hunyuanocr · prithivMLmods
Params539M
Context128K
Q4_K_M0.4 GB
Vision
QW
Qwen_Qwen3.8 Flash Next
Qwen · lmstudio-community
Params177B
Context256K
Q4_K_M119.2 GB
Vision
QW
Qwen3 4B
Qwen · lmstudio-community
Params4B
Context32K
Q4_K_M2.5 GB
GGUF
GE
Gemma 4 Writers 31B V2
Gemma · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
Roleplay
MA
MN 12B Mag Mell R1
Mag · bartowski
Params12.2B
Context1000K
Q4_K_M7.5 GB
Reasoning
HO
K2 Horizon MoVA 36B A4B Uncensored
Horizon · mradermacher
Params37.4B
Context512K
Q4_K_M22.4 GB
GGUF
OM
Omega Arsenal 31B Final
Omega · ReadyArt
Params30.7B
Context256K
Q4_K_M18.7 GB
Roleplay
JE
Jebadiah 9b v2
Jebadiah · frontier-infra
Params9.2B
Context256K
Q4_K_M5.8 GB
GGUF
EU
L3.3 70B Euryale v2.3
Euryale · bartowski
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
OL
allenai_olmOCR 2 7B 1025
OLMo · lmstudio-community
Params7.62B
Context125K
Q4_K_M4.7 GB
Vision
QW
Qwen38 27b Heretic Ara
Qwen · cygnal
Params27.3B
Context256K
Q4_K_M16.8 GB
Vision
QW
Qwen3-235B-A22B
Qwen · unsloth
Params235B
Context40K
Q4_K_M142.2 GB
GGUF
QW
Qwen2.5 Coder 32B Instruct Uncensored
Qwen · mradermacher
Params32.8B
Context32K
Q4_K_M19.9 GB
Coding
QW
Swift Qwen3.8 27b
Qwen · bartowski
Params27.3B
Context256K
Q4_K_M17.4 GB
ReasoningVision
MI
Mistral-Medium-3.5-128B
Mistral · unsloth
Params125B
Context256K
Q4_K_M74.9 GB
Vision
QW
Qwen3.5 4B Claude 4.6 Opus Reasoning Distilled v2
Qwen · Jackrong
Params4.2B
Context256K
Q4_K_M2.7 GB
ReasoningVision
TR
Translategemma 27b It
Translategemma · mradermacher
Params27B
Context128K
Q4_K_M16.5 GB
Vision

Other quants

Keep browsing