IQ2_M GGUF models
A GGUF quantization format. Lower numbers mean smaller files and more quality loss. 28351 models have a IQ2_M file. Sizes run from 2M to 1030B parameters. The longest trained context is 10240K tokens.
What is IQ2_M?
A GGUF quantization format. Lower numbers mean smaller files and more quality loss. On average it stores about 2.7 bits per weight, so a IQ2_M file is roughly 17% 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.
28,351 models have a IQ2_M file on ggufmodels.com, and those files range from 0.0 to 353.6 GB. The most downloaded are Qwen3.8 27B Uncensored, Qwen3.8 27B Uncensored HauhauCS Aggressive 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 IQ2_M in GGUF?
A GGUF quantization format. Lower numbers mean smaller files and more quality loss. It averages about 2.7 bits per weight.
Should I use IQ2_M?
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_M file?
IQ2_M files on this site range from 0.0 to 353.6 GB, depending on the model. As a rule of thumb it is about 17% of the 16-bit size.