Q4_K_S GGUF models

4-bit k-quant, small. Slightly smaller and a little lower quality than Q4_K_M. 104639 models have a Q4_K_S file. Sizes run from 1M to 1030B parameters. The longest trained context is 4194304K tokens.

Most downloadedNewestLargestLongest contextSmallest
MI
Mistral-7B-Instruct-v0.3
Mistral · bartowski
Params7.25B
Context32K
Q4_K_M4.4 GB
GGUF
QW
Qwen3 Coder Next
Qwen · bartowski
Params80B
Context256K
Q4_K_M48.7 GB
Coding
GE
Huihui Gemma 4 26B A4B It Abliterated
Gemma · groxaxo
Params25.2B
Context256K
Q4_K_M16.9 GB
Vision
QW
Qwen2.5 14B Uncensored Instruct
Qwen · bartowski
Params14.8B
Context128K
Q4_K_M9.0 GB
GGUF
LL
Llama 3.2 8X3B MOE Dark Champion Instruct uncensored abliterated 18.4B
Llama · DavidAU
Params18.4B
Context128K
Q4_K_M11.3 GB
Roleplay
LL
Llama-3.3-70B-Instruct
Llama · unsloth
Params70.6B
Context128K
Q4_K_M42.5 GB
GGUF
FL
FLUX 3 Image Klein GGUFs
Flux · realrebelai
Params5.54B
Context—
Q4_K_M3.4 GB
GGUF
FB
fblgit juanako 7b UNA
Fblgit · RichardErkhov
Params7.24B
Context—
Q4_K_M0.0 GB
GGUF
QW
Qwen3 4b Z Image Turbo AbliteratedV1
Qwen · BennyDaBall
Params4B
Context40K
Q4_K_M2.5 GB
GGUF
QW
Qwen3.8-27B-RANA-abliterated
Qwen · abliterant
Params27B
Context256K
Q4_K_M16.5 GB
Vision
MI
mistralai_mistral-7b-instruct-v0.1
Mistral · TheBloke
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
DE
DeepSeek R1 Distill Qwen 1.5B
DeepSeek · bartowski
Params1.78B
Context128K
Q4_K_M1.1 GB
Reasoning
QW
Qwen3 8B
Qwen · bartowski
Params8.19B
Context32K
Q4_K_M5.0 GB
GGUF
QW
Qwen2.5 Coder 32B Instruct
Qwen · bartowski
Params32.8B
Context32K
Q4_K_M19.9 GB
Coding
QW
Qwen3.5 9B Abliterated
Qwen · Abiray
Params8.95B
Context256K
Q4_K_M5.6 GB
Vision
PH
Phi 3.5 Mini Instruct
Phi · bartowski
Params3.82B
Context128K
Q4_K_M2.4 GB
Coding
LL
Dolphin 3.0 Llama 3.1 8B
Llama · bartowski
Params8B
Context128K
Q4_K_M4.9 GB
CodingTool use
ME
Medgemma-4B-It
Medgemma · unsloth
Params3.88B
Context128K
Q4_K_M2.5 GB
ReasoningVision
QW
Qwen3 14B Abliterated
Qwen · bartowski
Params14.8B
Context40K
Q4_K_M9.0 GB
GGUF
GE
Gemma 4 26B A4B It Uncensored Heretic
Gemma · llmfan46
Params25.2B
Context256K
Q4_K_M16.8 GB
Vision
QW
Qwen3-Next-80B-A3B-Thinking
Qwen · unsloth
Params80B
Context256K
Q4_K_M48.5 GB
Reasoning
CY
z image cyberrealistic v9
Cyberrealistic · gimly13
Params6.15B
Context40K
Q4_K_M2.5 GB
GGUF
GL
Glm 5.3 Flash Reap50 Fp8 Pass2
GLM · patrickbdevaney
Params165B
Context1024K
Q4_K_M99.3 GB
ReasoningTool useVision
TI
py007_tinyllama-1.1b-chat-v0.3
Tinyllama · TheBloke
Params1.1B
Context2K
Q4_K_M0.7 GB
Coding
GE
Gemma 4 31B It
Gemma · bartowski
Params30.7B
Context256K
Q4_K_M19.6 GB
Vision
MI
Mimo-V2-Flash
Mimo · unsloth
Params310B
Context256K
Q4_K_M186.8 GB
GGUF
WA
wan 1.3b
Wan · calcuis
Params127M
Context—
Q4_K_M1.0 GB
GGUF
QW
Qwen2.5-VL-3B-Instruct
Qwen · Mungert
Params3.1B
Context125K
Q4_K_M1.9 GB
Vision
GL
GLM 4.7 Flash Uncensored Heretic NEO CODE Imatrix MAX
GLM · DavidAU
Params29.9B
Context198K
Q4_K_M18.5 GB
CodingReasoningRoleplay
GE
Gemma 2 2b It
Gemma · bartowski
Params2.61B
Context8K
Q4_K_M1.7 GB
GGUF

Other quants

Keep browsing