IQ3_XS GGUF models
A GGUF quantization format. Lower numbers mean smaller files and more quality loss. 46199 models have a IQ3_XS file. Sizes run from 1M to 1030B parameters. The longest trained context is 102400K tokens.
What is IQ3_XS?
A GGUF quantization format. Lower numbers mean smaller files and more quality loss. On average it stores about 3.3 bits per weight, so a IQ3_XS file is roughly 21% 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.
46,199 models have a IQ3_XS file on ggufmodels.com, and those files range from 0.0 to 466.6 GB. The most downloaded are Qwen3.8 27B Uncensored HauhauCS Aggressive MTP, Qwen3.8 27B and MiMo V2.6 Distill Qwen 9B. For a longer explanation of every quant type, read GGUF quantization explained.
Frequently asked questions
What is IQ3_XS in GGUF?
A GGUF quantization format. Lower numbers mean smaller files and more quality loss. It averages about 3.3 bits per weight.
Should I use IQ3_XS?
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 IQ3_XS file?
IQ3_XS files on this site range from 0.0 to 466.6 GB, depending on the model. As a rule of thumb it is about 21% of the 16-bit size.