IQ4_XS GGUF models
Importance-matrix 4-bit quant, extra small. Small files with good quality for the size. 97368 models have a IQ4_XS file. Sizes run from 1M to 2450B parameters. The longest trained context is 102400K tokens.
What is IQ4_XS?
Importance-matrix 4-bit quant, extra small. Small files with good quality for the size. On average it stores about 4.3 bits per weight, so a IQ4_XS file is roughly 27% of the size of the same model in 16-bit. The usual sweet spot between file size and quality, and the quant most people start with.
97,368 models have a IQ4_XS file on ggufmodels.com, and those files range from 0.0 to 1310.9 GB. The most downloaded are Qwen3.8-27B, Qwen3.8-27B and Tiel Coder 35B A3B GGUF MTP. For a longer explanation of every quant type, read GGUF quantization explained.
Frequently asked questions
What is IQ4_XS in GGUF?
Importance-matrix 4-bit quant, extra small. Small files with good quality for the size. It averages about 4.3 bits per weight.
Should I use IQ4_XS?
The usual sweet spot between file size and quality, and the quant most people start with.
How big is a IQ4_XS file?
IQ4_XS files on this site range from 0.0 to 1310.9 GB, depending on the model. As a rule of thumb it is about 27% of the 16-bit size.