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
JA
Jan v2 VL med
Jan · janhq
Params8.2B
Context256K
Q4_K_M5.0 GB
Vision
QW
Qwen3.5 2B Uncensored Zero Refusal SOMA
Qwen · AkaumiKaede
Params1.88B
Context256K
Q4_K_M1.3 GB
RoleplayVision
LI
Ling Flash 2.0
Ling · bartowski
Params103B
Context32K
Q4_K_M62.6 GB
GGUF
AM
amalia-llm/AMALIA-9B-0626-DPO
Amalia · layerx-labs
Params9.15B
Context32K
Q4_K_M5.6 GB
GGUF
QW
Qwen3.5 9b Uncensored
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
Tool use
RA
MS Raven 24B v1
Raven · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
Roleplay
GE
Gemma 3 12b It Vl Kimi V2 Heretic Uncensored Thinking
Gemma · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
ReasoningVision
LF
LFM3-1.7B
Lfm · AtomicChat
Params1.73B
Context256K
Q4_K_M1.1 GB
ReasoningTool use
LL
Meta Llama 3.1 8B Instruct
Llama · joshnader
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
CA
Carnice-V2-27B
Carnice · kai-os
Params27B
Context256K
Q4_K_M16.5 GB
Tool use
CH
AA Chameleon 7b Base
Chameleon · mradermacher
Params7B
Context4K
Q4_K_M4.3 GB
GGUF
WR
Wren
Wren · ohmysimo
Params117B
Context256K
Q4_K_M77.6 GB
GGUF
QW
MiMo V2.6 Distill Qwen 9B Heretic
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
CodingReasoningRoleplay
QW
Qwen3.8-27B
Qwen · xrachelburns
Params27.3B
Context256K
Q4_K_M16.6 GB
Vision
HU
Hunyuan 7B Instruct
Hunyuan · bartowski
Params7.5B
Context256K
Q4_K_M4.6 GB
GGUF
QW
Huihui Qwen3.8 27B Abliterated
Qwen · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
GGUF
MI
Mimo-V2.5-Pro
Mimo · unsloth
Params1020B
Context1024K
Q4_K_M629.6 GB
Coding
GE
Gemma 3n E4B It
Gemma · bartowski
Params6.9B
Context32K
Q4_K_M4.2 GB
GGUF
LO
LongCat Video Avatar ComfyUI
Longcat · vantagewithai
Params15.9B
Context—
Q4_K_M12.0 GB
GGUF
LU
lumina
Lumina · calcuis
Params2.61B
Context—
Q4_K_M1.5 GB
GGUF
QW
Qwen3 Coder 30B A3B Instruct RTPurbo
Qwen · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
Coding
LL
CodeLlama 7b Python Hf
Llama · mradermacher
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding
QW
Qwen3.5 35B A3B Base
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
Vision
TO
Torchcast Decision 27b
Torchcast · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
GGUF
QW
Qwen3.5 122B A10B Heretic
Qwen · mradermacher
Params122B
Context256K
Q4_K_M74.2 GB
Vision
AR
Artex Coder 7b
Artex · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
Coding
QW
Qwen25 Coder 3b Claude
Qwen · ryzdfm
Params3.09B
Context32K
Q4_K_M1.9 GB
CodingReasoning
MT
Mtrini SVL 2.0
Mtrini · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool use
LA
Laguna-XS-2.1
Laguna · ggml-org
Params33.4B
Context256K
Q4_K_M19.6 GB
GGUF
QW
Rice Cracker Qwen3.5 0.8B Abliterated Base
Qwen · mradermacher
Params752M
Context256K
Q4_K_M0.5 GB
Coding

Other quants

Keep browsing