Q4_0 GGUF models
Older 4-bit format. Q4_K_M is usually a better choice at a similar size. 54307 models have a Q4_0 file. Sizes run from 1M to 1570B parameters. The longest trained context is 4194304K tokens.
What is Q4_0?
Older 4-bit format. Q4_K_M is usually a better choice at a similar size. On average it stores about 4.5 bits per weight, so a Q4_0 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.
54,307 models have a Q4_0 file on ggufmodels.com, and those files range from 0.0 to 885.3 GB. The most downloaded are Qwen3.8-27B, Qwen3.8 Flash Next GSQ RCO abliterated and Qwen3.8 27B Uncensored. For a longer explanation of every quant type, read GGUF quantization explained.
Frequently asked questions
What is Q4_0 in GGUF?
Older 4-bit format. Q4_K_M is usually a better choice at a similar size. It averages about 4.5 bits per weight.
Should I use Q4_0?
The usual sweet spot between file size and quality, and the quant most people start with.
How big is a Q4_0 file?
Q4_0 files on this site range from 0.0 to 885.3 GB, depending on the model. As a rule of thumb it is about 28% of the 16-bit size.