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
EA
EAN 8B i1
Ean · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
Tool use
LL
openassistant_llama2-13b-orca-8k-3319
Llama · TheBloke
Params13B
Context8K
Q4_K_M7.9 GB
GGUF
LF
Atomic Chat / LFM2.5 8B A1B
Lfm · AlexAtomic
Params8.47B
Context125K
Q4_K_M5.2 GB
GGUF
WI
Wicked Stuff 26B A4B v3.0 Final
Wicked · ReadyArt
Params25.2B
Context256K
Q4_K_M16.8 GB
ReasoningRoleplayTool use
NE
NVIDIA Nemotron 3 Nano 30B A3B
Nemotron · lmstudio-community
Params31.6B
Context1024K
Q4_K_M24.5 GB
GGUF
LL
ehartford_samantha-1.11-codellama-34b
Llama · TheBloke
Params33.7B
Context2K
Q4_K_M20.2 GB
Coding
GE
DiarizationLM Gemma 4 E4B v1
Gemma · diarizers-community
Params7.46B
Context128K
Q4_K_M5.3 GB
Vision
SW
Swallow-7b-NVE-instruct-hf
Swallow · mradermacher
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
QW
Huihui Qwen3.5 27B Abliterated
Qwen · HeYujie
Params27B
Context256K
Q4_K_M16.5 GB
Vision
MI
MiniCPM5 1B Claude Opus Fable5 V2 Thinking heretic
MiniCPM · saidutta69
Params1.08B
Context128K
Q4_K_M0.7 GB
ReasoningRoleplayTool use
QW
Qwen3.5 122B A10B Heretic v2
Qwen · mradermacher
Params122B
Context256K
Q4_K_M74.2 GB
GGUF
LF
LFM2.5-24B-A2B
Lfm · ggml-org
Params24B
Context128K
Q4_K_M14.5 GB
ReasoningTool use
MI
Mistral Nemo Inst 2407 12B Thinking Uncensored HERETIC HI Claude Opus
Mistral · mradermacher
Params12.2B
Context1000K
Q4_K_M7.5 GB
ReasoningRoleplay
LL
Llama 3.2 3B Instruct
Llama · mradermacher
Params3.61B
Context128K
Q4_K_M2.2 GB
GGUF
LL
LightGPT 13B Llama2
Llama · mradermacher
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
GE
Huihui Gemma 4 E2B It Abliterated
Gemma · mradermacher
Params4.65B
Context128K
Q4_K_M3.4 GB
Vision
QW
Qwen2.5 Coder 32B Instruct
Qwen · lmstudio-community
Params32.8B
Context32K
Q4_K_M19.9 GB
Coding
BE
Bernini R GGUF ComfyUI
Bernini · vantagewithai
Params14.3B
Context—
Q4_K_M9.7 GB
GGUF
JA
japanese stablelm instruct beta 70B
Japanese · TheBloke
Params69B
Context4K
Q4_K_M41.4 GB
GGUF
DA
Dans PersonalityEngine V1.1.0 12b
Dans · bartowski
Params12.2B
Context1000K
Q4_K_M7.5 GB
CodingRoleplay
YI
01 ai Yi 6B
Yi · RichardErkhov
Params6.06B
Context4K
Q4_K_M3.7 GB
GGUF
KR
Kronumos Kairos v2
Kronumos · mradermacher
Params7.6B
Context32K
Q4_K_M4.7 GB
Coding
SE
SexyGPT v3 Thinking Female
Sexygpt · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
ReasoningRoleplayVision
PS
Psyonic Cetacean Ultra Quality 20b GGUF imatrix
Psyonic · DavidAU
Params20B
Context4K
Q4_K_M12.0 GB
Roleplay
CA
Carnice V3
Carnice · bartowski
Params27.3B
Context256K
Q4_K_M17.8 GB
Tool useVision
LI
Ling 3.1 Flash
Ling · bartowski
Params572B
Context256K
Q4_K_M358.0 GB
GGUF
ME
Meltemi 7B Instruct v1
Meltemi · mradermacher
Params7.48B
Context32K
Q4_K_M4.5 GB
GGUF
QW
Qwen3.8-Flash-Next-DFlash2
Qwen · incoai
Params603M
Context256K
Q4_K_M0.4 GB
ReasoningTool use
CL
clef flash
Clef · NANI-Nithin
Params8.95B
Context256K
Q4_K_M5.6 GB
GGUF
MO
Morpho 7B Distill
Morpho · mradermacher
Params7.62B
Context128K
Q4_K_M4.7 GB
GGUF

Other quants

Keep browsing