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
HU
Hunyuan-MT-7B
Hunyuan · Mungert
Params7.5B
Context256K
Q4_K_M4.7 GB
GGUF
QW
Jev Style Qwen3.5 2B Decision
Qwen · chaoliangUNSW
Params1.94B
Context256K
Q4_K_M1.3 GB
GGUF
QW
Qwen Image 2.1 Text Encoder
Qwen · darrellbest
Params8.2B
Context256K
Q4_K_M5.7 GB
CodingVision
PH
phi 4
Phi · bartowski
Params14.7B
Context16K
Q4_K_M9.1 GB
Coding
OM
Omega Arsenal 31B Final
Omega · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
ReasoningTool use
LT
LTX Video 0.9.6 distilled
Ltx · city96
Params1.92B
Context—
Q4_K_M1.3 GB
GGUF
QW
Qwen3.8 27B
Qwen · DhruvalLabs
Params27.3B
Context256K
Q4_K_M16.8 GB
Vision
FL
FLUX.1 Kontext dev
Flux · unsloth
Params11.9B
Context—
Q4_K_M7.4 GB
GGUF
GE
Ablation 188 Gemma3.Webnovels.Test.Gemma 3 12b
Gemma · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
GGUF
SM
SmolLM2 135M Instruct
SmolLM · mradermacher
Params135M
Context8K
Q4_K_M0.1 GB
GGUF
ME
G4 MeroMero v2 31B
Meromero · zerofata
Params30.7B
Context256K
Q4_K_M18.7 GB
GGUF
QW
Qwen2.5-14B-Instruct-1M
Qwen · Mungert
Params14.8B
Context986K
Q4_K_M9.2 GB
GGUF
QW
Qwen3.8 27B
Qwen · KikoCis
Params26.9B
Context256K
Q4_K_M16.8 GB
ReasoningTool use
MI
Mistral-7B-Instruct-v0.3
Mistral · lmstudio-community
Params7.25B
Context32K
Q4_K_M4.4 GB
GGUF
MI
MiniCPM V 4.7 1B abliterated heretic
MiniCPM · Abiray
Params1.01B
Context256K
Q4_K_M0.7 GB
Vision
QW
Qwen3.8 27B Q4 K M
Qwen · Abiray
Params27.3B
Context256K
Q4_K_M16.8 GB
Vision
QW
Qwen3 Coder 30B A3B
Qwen · AtomicChat
Params30.5B
Context256K
Q4_K_M18.6 GB
CodingTool use
QW
Qwen3.5 9B Heretic
Qwen · darrellbest
Params9.2B
Context256K
Q4_K_M5.8 GB
Vision
QW
Qwen3.8-27B-Abliterated
Qwen · windowsxp811203
Params27.3B
Context256K
Q4_K_M16.8 GB
Vision
LA
m51Lab MiniMax M2.7 REAP 139B A10B
Lab · mradermacher
Params139B
Context192K
Q4_K_M84.2 GB
GGUF
GE
avemio digital gemma 2b Sft pretrain 6000 steps merge
Gemma · RichardErkhov
Params2.5B
Context8K
Q4_K_M1.6 GB
GGUF
QW
Qwen2.5 7B Instruct
Qwen · paultimothymooney
Params7.62B
Context32K
Q4_K_M4.7 GB
GGUF
IN
InternVL3_5 8B
Internvl · bartowski
Params8.19B
Context40K
Q4_K_M5.0 GB
Vision
LL
codellama_codellama-13b-instruct-hf
Llama · TheBloke
Params13B
Context16K
Q4_K_M7.9 GB
Coding
GE
gemma 4 E2B it
Gemma · AtomicChat
Params4.65B
Context128K
Q4_K_M3.4 GB
ReasoningTool use
HU
Humanizer
Humanizer · mradermacher
Params11.9B
Context256K
Q4_K_M7.4 GB
GGUF
NE
DictaLM 3.0 Nemotron 12B Instruct
Nemotron · dicta-il
Params12.3B
Context1024K
Q4_K_M7.5 GB
GGUF
GE
Gemma 2 9b It
Gemma · bartowski
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
ON
OneJev 27B
Onejev · bartowski
Params27B
Context256K
Q4_K_M17.2 GB
Vision
QW
Qwen3.8 27B
Qwen · prithivMLmods
Params27.3B
Context256K
Q4_K_M16.8 GB
ReasoningVision

Other quants

Keep browsing