Q4_K_M GGUF models
4-bit k-quant, medium. The common default: a good balance of size and quality. 148631 models have a Q4_K_M file. Sizes run from 1M to 2450B parameters. The longest trained context is 4194304K tokens.
What is Q4_K_M?
4-bit k-quant, medium. The common default: a good balance of size and quality. On average it stores about 4.9 bits per weight, so a Q4_K_M file is roughly 31% 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.
148,631 models have a Q4_K_M file on ggufmodels.com, and those files range from 0.0 to 1481.4 GB. The most downloaded are Qwen3.8-27B, Ornith-1.5-9B and Ornith-1.5-35B. For a longer explanation of every quant type, read GGUF quantization explained.
Frequently asked questions
What is Q4_K_M in GGUF?
4-bit k-quant, medium. The common default: a good balance of size and quality. It averages about 4.9 bits per weight.
Should I use Q4_K_M?
The usual sweet spot between file size and quality, and the quant most people start with.
How big is a Q4_K_M file?
Q4_K_M files on this site range from 0.0 to 1481.4 GB, depending on the model. As a rule of thumb it is about 31% of the 16-bit size.