IQ3_XXS GGUF models
A GGUF quantization format. Lower numbers mean smaller files and more quality loss. 28129 models have a IQ3_XXS file. Sizes run from 2M to 2450B parameters. The longest trained context is 10240K tokens.
What is IQ3_XXS?
A GGUF quantization format. Lower numbers mean smaller files and more quality loss. On average it stores about 3.1 bits per weight, so a IQ3_XXS file is roughly 19% 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.
28,129 models have a IQ3_XXS file on ggufmodels.com, and those files range from 0.0 to 955.5 GB. The most downloaded are Qwen3.8 Flash Next GSQ RCO, Qwen3.8-27B and Qwen3.8 Flash Next GSQ RCO abliterated. For a longer explanation of every quant type, read GGUF quantization explained.
Frequently asked questions
What is IQ3_XXS in GGUF?
A GGUF quantization format. Lower numbers mean smaller files and more quality loss. It averages about 3.1 bits per weight.
Should I use IQ3_XXS?
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_XXS file?
IQ3_XXS files on this site range from 0.0 to 955.5 GB, depending on the model. As a rule of thumb it is about 19% of the 16-bit size.