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.
What is Q3_K_S?
3-bit k-quant, small. Small files with noticeable quality loss. On average it stores about 3.5 bits per weight, so a Q3_K_S file is roughly 22% of the size of the same model in 16-bit. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
102,724 models have a Q3_K_S file on ggufmodels.com, and those files range from 0.0 to 1197.0 GB. The most downloaded are Ornith 1.5 9B Uncensored, Qwen Image 2.1 and Gemma-4-12B-It. For a longer explanation of every quant type, read GGUF quantization explained.
Frequently asked questions
What is Q3_K_S in GGUF?
3-bit k-quant, small. Small files with noticeable quality loss. It averages about 3.5 bits per weight.
Should I use Q3_K_S?
A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
How big is a Q3_K_S file?
Q3_K_S files on this site range from 0.0 to 1197.0 GB, depending on the model. As a rule of thumb it is about 22% of the 16-bit size.