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.
LL
phind_phind-codellama-34b-v2
Llama · TheBloke
Params33.7B
Context16K
Q4_K_M20.2 GB
GR
Granite-4.1-8B
Granite · unsloth
Params8.79B
Context128K
Q4_K_M5.3 GB
TO
Tongyi DeepResearch 30B A3B
Tongyi · bartowski
Params30.5B
Context128K
Q4_K_M18.6 GB
YI
01 ai Yi 34B
Yi · RichardErkhov
Params34.4B
Context4K
Q4_K_M20.7 GB
WA
Wan2.1 T2V 14B FusionX VACE
Wan · QuantStack
Params17.3B
Context—
Q4_K_M11.6 GB
FA
90m Instruct
Falcon · tiiuae
Params91M
Context256K
Q4_K_M0.1 GB
SE
Seed-Coder-8B-Reasoning
Seed · unsloth
Params8.25B
Context64K
Q4_K_M5.1 GB
QW
Qwen3.5 9B Heretic Ara v1
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
QW
Qwen3.5 35B A3B Heretic
Qwen · mradermacher
Params34.7B
Context256K
Q4_K_M21.2 GB
LL
archangel_sft-kto_llama30b
Llama · mradermacher
Params32.5B
Context2K
Q4_K_M19.6 GB
MI
Ministral 3 14B Abliterated
Mistral · mradermacher
Params13.5B
Context256K
Q4_K_M8.2 GB
MI
Minimax-M2.7
Minimax · unsloth
Params230B
Context192K
Q4_K_M140.2 GB
LL
nousresearch_yarn-llama-2-13b-128k
Llama · TheBloke
Params13B
Context128K
Q4_K_M7.9 GB
LL
nousresearch_yarn-llama-2-13b-64k
Llama · TheBloke
Params13B
Context64K
Q4_K_M7.9 GB
GE
Gemma 3 1b It Abliterated
Gemma · bartowski
Params1B
Context32K
Q4_K_M0.8 GB
GA
GameScaling 9B S3
Gamescaling · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
GE
Baihua Gemma4 E4B
Gemma · mradermacher
Params7.46B
Context128K
Q4_K_M5.3 GB
GE
gemma 4 E4B it heretic
Gemma · saidutta69
Params7.46B
Context128K
Q4_K_M5.3 GB
D1
d1 3B
NANI-Nithin
Params2.7B
Context32K
Q4_K_M1.7 GB
PY
ajibawa-2023_python-code-33b
Python · TheBloke
Params32.5B
Context2K
Q4_K_M19.6 GB
QW
Qwen2.5 14B Instruct 1M
Qwen · bartowski
Params14.8B
Context986K
Q4_K_M9.0 GB
GE
Huihui Gemma 4 26B A4B It Abliterated
Gemma · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
DA
Dans PersonalityEngine V1.3.0 24b
Dans · bartowski
Params23.6B
Context128K
Q4_K_M14.3 GB
DE
DeepSeek Coder V2 Lite Instruct Abliterated
DeepSeek · mradermacher
Params15.7B
Context160K
Q4_K_M10.4 GB
GR
Granite 4.0 1b
Granite · ibm-granite
Params1.63B
Context128K
Q4_K_M1.0 GB
AR
Arctic Text2SQL R1 7B
Arctic · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
GR
Granite 20b Code Instruct 8k
Granite · mradermacher
Params20B
Context8K
Q4_K_M12.8 GB
QU
QuartetAnemoi 70B t0.0001
Quartetanemoi · backyardai
Params69B
Context32K
Q4_K_M41.4 GB
LL
Llama xLAM 2 8b Fc R
Llama · Salesforce
Params8B
Context128K
Q4_K_M4.9 GB
MI
Devstral-Small-2505
Mistral · unsloth
Params23.6B
Context128K
Q4_K_M14.3 GB