Q5_K_S GGUF models
5-bit k-quant, small. Closer to the original quality than Q4, at a larger size. 103100 models have a Q5_K_S file. Sizes run from 1M to 1030B parameters. The longest trained context is 4194304K tokens.
What is Q5_K_S?
5-bit k-quant, small. Closer to the original quality than Q4, at a larger size. On average it stores about 5.5 bits per weight, so a Q5_K_S file is roughly 34% of the size of the same model in 16-bit. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
103,100 models have a Q5_K_S file on ggufmodels.com, and those files range from 0.0 to 713.2 GB. The most downloaded are Qwen3.8-27B, Tiel Coder 35B A3B GGUF MTP and Qwen3.5 9B The Defiant Fable Uncensored Heretic NEO IMATRIX MAX MTP. For a longer explanation of every quant type, read GGUF quantization explained.
Frequently asked questions
What is Q5_K_S in GGUF?
5-bit k-quant, small. Closer to the original quality than Q4, at a larger size. It averages about 5.5 bits per weight.
Should I use Q5_K_S?
Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
How big is a Q5_K_S file?
Q5_K_S files on this site range from 0.0 to 713.2 GB, depending on the model. As a rule of thumb it is about 34% of the 16-bit size.