IQ2_XXS GGUF models
Importance-matrix 2-bit quant. Extreme compression with a large quality cost. 26647 models have a IQ2_XXS file. Sizes run from 2M to 2780B parameters. The longest trained context is 10240K tokens.
What is IQ2_XXS?
Importance-matrix 2-bit quant. Extreme compression with a large quality cost. On average it stores about 2.1 bits per weight, so a IQ2_XXS file is roughly 13% of the size of the same model in 16-bit. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
26,647 models have a IQ2_XXS file on ggufmodels.com, and those files range from 0.0 to 769.1 GB. The most downloaded are Qwen3.8-27B, Qwen3.8 27B and DeepSeek V4.1 Flash 1017 GSQ RCO. For a longer explanation of every quant type, read GGUF quantization explained.
Frequently asked questions
What is IQ2_XXS in GGUF?
Importance-matrix 2-bit quant. Extreme compression with a large quality cost. It averages about 2.1 bits per weight.
Should I use IQ2_XXS?
Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
How big is a IQ2_XXS file?
IQ2_XXS files on this site range from 0.0 to 769.1 GB, depending on the model. As a rule of thumb it is about 13% of the 16-bit size.