IQ4_NL GGUF models
A GGUF quantization format. Lower numbers mean smaller files and more quality loss. 32452 models have a IQ4_NL file. Sizes run from 1M to 1030B parameters. The longest trained context is 102400K tokens.
What is IQ4_NL?
A GGUF quantization format. Lower numbers mean smaller files and more quality loss. On average it stores about 4.5 bits per weight, so a IQ4_NL file is roughly 28% of the size of the same model in 16-bit. The usual sweet spot between file size and quality, and the quant most people start with.
32,452 models have a IQ4_NL file on ggufmodels.com, and those files range from 0.0 to 580.0 GB. The most downloaded are Qwen3.5 9B The Defiant Fable Uncensored Heretic NEO IMATRIX MAX MTP, Gemma-4-12B-It 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 IQ4_NL in GGUF?
A GGUF quantization format. Lower numbers mean smaller files and more quality loss. It averages about 4.5 bits per weight.
Should I use IQ4_NL?
The usual sweet spot between file size and quality, and the quant most people start with.
How big is a IQ4_NL file?
IQ4_NL files on this site range from 0.0 to 580.0 GB, depending on the model. As a rule of thumb it is about 28% of the 16-bit size.