IQ1_M GGUF models
A GGUF quantization format. Lower numbers mean smaller files and more quality loss. 25682 models have a IQ1_M file. Sizes run from 2M to 2780B parameters. The longest trained context is 10240K tokens.
What is IQ1_M?
A GGUF quantization format. Lower numbers mean smaller files and more quality loss. On average it stores about 1.8 bits per weight, so a IQ1_M file is roughly 11% 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.
25,682 models have a IQ1_M file on ggufmodels.com, and those files range from 0.0 to 689.9 GB. The most downloaded are Qwen3.8-27B, DeepSeek V4.1 Flash 1017 GSQ RCO and Qwen3.6-35B-A3B. For a longer explanation of every quant type, read GGUF quantization explained.
Frequently asked questions
What is IQ1_M in GGUF?
A GGUF quantization format. Lower numbers mean smaller files and more quality loss. It averages about 1.8 bits per weight.
Should I use IQ1_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 IQ1_M file?
IQ1_M files on this site range from 0.0 to 689.9 GB, depending on the model. As a rule of thumb it is about 11% of the 16-bit size.