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
QW
ThinkingCap Qwen3.8 27B
Qwen · mradermacher
Params27.3B
Context256K
Q4_K_M16.8 GB
Reasoning
FE
Fenrir X 26B A4B
Fenrir · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
Roleplay
AM
Amaretto 14B
Amaretto · mradermacher
Params13.5B
Context256K
Q4_K_M8.2 GB
Tool use
QW
Qwen3.5 4B Claude 3xMerge Jackrong UNCENSORED Heretic
Qwen · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool use
CY
CyberRealisticXL
Cyberrealisticxl · InsecureErasure
Params2.57B
Context—
Q4_K_M1.6 GB
GGUF
GR
granite-3b-code-instruct
Granite · mradermacher
Params3.48B
Context2K
Q4_K_M2.1 GB
CodingTool use
MI
MiniCPM o 2 6
MiniCPM · openbmb
Params7.6B
Context32K
Q4_K_M4.7 GB
Vision
MI
Mistral 7B Instruct v0.1
Mistral · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
JA
japanese stablelm instruct beta 7B
Japanese · TheBloke
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
MI
Mistral Nemo Instruct 2407 abliterated
Mistral · QuantFactory
Params12.2B
Context1000K
Q4_K_M7.5 GB
GGUF
HU
Huihui Ornith 1.5 9B Abliterated
Huihui · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
Vision
MI
Voxtral Mini 3B 2507
Mistral · bartowski
Params4.01B
Context128K
Q4_K_M2.5 GB
Vision
VI
Viking-33B
Viking · mradermacher
Params33B
Context4K
Q4_K_M20.0 GB
Coding
YI
ehartford_dolphin-2_2-yi-34b
Yi · TheBloke
Params34.4B
Context16K
Q4_K_M20.7 GB
GGUF
OP
openchat_openchat-3.5-1210
Openchat · TheBloke
Params7.24B
Context8K
Q4_K_M4.4 GB
Coding
MI
MiniCPM V 4_6 Thinking
MiniCPM · openbmb
Params752M
Context256K
Q4_K_M0.5 GB
ReasoningVision
HU
humanizer-12b
Humanizer · ngquocvinh
Params11.9B
Context256K
Q4_K_M7.4 GB
GGUF
AE
AesCode 8B
Aescode · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
Coding
OR
Ornith 1.0 9B
Ornith · bartowski
Params8.95B
Context256K
Q4_K_M5.9 GB
Vision
QW
JoyFox Qwen3.6 35B A3B RP Aggressive
Qwen · mradermacher
Params35.5B
Context256K
Q4_K_M21.7 GB
RoleplayVision
GR
Granite-4.0-H-Small
Granite · unsloth
Params32.2B
Context1024K
Q4_K_M19.6 GB
GGUF
GE
Gemma 4 31B It Scotoma 2
Gemma · bartowski
Params30.7B
Context256K
Q4_K_M19.6 GB
Vision
TE
tensor bank
Tensor · gguf-org
Params—
Context—
Q4_K_M0.0 GB
GGUF
LL
LLaMA Mesh
Llama · bartowski
Params8B
Context128K
Q4_K_M4.9 GB
GGUF
QW
Whittle Qwen 3.8 35B A3B
Qwen · mradermacher
Params35.5B
Context256K
Q4_K_M21.3 GB
CodingReasoning
MI
Ministral 3 8B Instruct 2512
Mistral · bartowski
Params8.49B
Context256K
Q4_K_M5.2 GB
Vision
QW
Qwen2.5 VL 32B Geometry
Qwen · mradermacher
Params32.8B
Context125K
Q4_K_M19.9 GB
Vision
QW
UnifiedReward Edit Qwen35 27b
Qwen · mradermacher
Params26.9B
Context256K
Q4_K_M16.5 GB
ReasoningTool useVision
AE
AesCode 8B
Aescode · prithivMLmods
Params8.19B
Context256K
Q4_K_M5.0 GB
CodingVision
LL
tulu v1 llama2 70b i1
Llama · mradermacher
Params69B
Context2K
Q4_K_M41.4 GB
GGUF

Other quants

Keep browsing