Q3_K_S GGUF models

3-bit k-quant, small. Small files with noticeable quality loss. 102724 models have a Q3_K_S file. Sizes run from 1M to 2780B parameters. The longest trained context is 4194304K tokens.

Most downloadedNewestLargestLongest contextSmallest
GR
Granite 4.0 Micro
Granite · ibm-granite
Params3.4B
Context128K
Q4_K_M2.1 GB
GGUF
NE
Nex N2.5 mini
Nex · abenzerps
Params34.7B
Context256K
Q4_K_M21.2 GB
Tool useVision
SE
Sexpedition MS3.2 24B
Sexpedition · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
QW
Huihui Qwen3 8B Abliterated v2
Qwen · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
GGUF
DE
deepseek-ai_deepseek-coder-33b-base
DeepSeek · TheBloke
Params33.3B
Context16K
Q4_K_M19.9 GB
Coding
DA
L3 Dark Planet 8B
Dark · DavidAU
Params8B
Context8K
Q4_K_M5.1 GB
Roleplay
GE
Gemma 4 26B A4B It Uncensored
Gemma · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
ReasoningTool use
LT
LTX Video
Ltx · city96
Params1.92B
Context—
Q4_K_M1.4 GB
GGUF
QW
Qwen2.5 VL 7B Abliterated Caption It
Qwen · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
Vision
MI
dolphin 2.9.3 mistral nemo 12b
Mistral · dphn
Params12.2B
Context1000K
Q4_K_M7.5 GB
CodingTool use
QW
Qwen3 VL Reranker 8B
Qwen · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
EmbeddingVision
OR
Ornith1.0 9B 3MPER0RR Abliterated
Ornith · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool use
AR
Artemis 31B v1.1
Artemis · bartowski
Params30.7B
Context256K
Q4_K_M19.6 GB
Vision
ON
OneJev 4B
Onejev · mradermacher
Params4.84B
Context256K
Q4_K_M3.1 GB
Vision
QW
Qwen3.6 35B A3B
Qwen · byteshape
Params34.7B
Context256K
Smallest9.4 GB
Vision
QW
Models Qwen Qwen2 Math 72B Instruct
Qwen · MaziyarPanahi
Params72.7B
Context4K
Q4_K_M47.4 GB
GGUF
JE
JEV 27B VL Uncensored
Jev · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
Vision
PU
PuddleJumper 13B
Puddlejumper · TheBloke
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
ST
berkeley-nest_starling-lm-7b-alpha
Starling · TheBloke
Params7.24B
Context8K
Q4_K_M4.4 GB
GGUF
QW
Qwen3 14B ARPO DeepSearch
Qwen · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
Tool use
MY
Mythos v2 9b
Mythos · fableforge-ai
Params9.2B
Context256K
Q4_K_M5.8 GB
Tool use
HO
Holo 3.1 4B
Holo · mradermacher
Params4.84B
Context256K
Q4_K_M3.1 GB
ReasoningTool useVision
IN
Index Anisora V3.2
Index · youcef079
Params14.3B
Context—
Q4_K_M10.1 GB
GGUF
TO
tokyotech llm Swallow MS 7b instruct v0.1
Tokyotech · mmnga
Params7.33B
Context4K
Q4_K_M4.4 GB
GGUF
QW
qwen image edit plus
Qwen · calcuis
Params14.3B
Context—
Q4_K_M11.7 GB
GGUF
LL
codellama_codellama-34b-hf
Llama · TheBloke
Params33.7B
Context16K
Q4_K_M20.2 GB
Coding
XO
Xor 26B A4B
Xor · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
GGUF
PR
Promethean Dawn 26B A4B
Promethean · mradermacher
Params26B
Context256K
Q4_K_M17.2 GB
Roleplay
EM
Source Hf Embeddinggemma 2
Embeddinggemma · ngquocvinh
Params271M
Context256K
Q4_K_M0.2 GB
EmbeddingVision
LF
LFM2.5 24B A2B Uncensored Heretic
Lfm · mradermacher
Params24B
Context128K
Q4_K_M14.5 GB
GGUF

Other quants

Keep browsing