F16 GGUF models
Unquantized 16-bit floats. Original quality and the largest size. 53239 models have a F16 file. Sizes run from 0M to 1030B parameters. The longest trained context is 10742K tokens.
What is F16?
Unquantized 16-bit floats. Original quality and the largest size. On average it stores about 16 bits per weight, so a F16 file is roughly 100% of the size of the same model in 16-bit. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
53,239 models have a F16 file on ggufmodels.com, and those files range from 0.0 to 2053.2 GB. The most downloaded are locate anything.cpp, Qwen3.8-27B and mxbai-embed-large-v1. For a longer explanation of every quant type, read GGUF quantization explained.
Frequently asked questions
What is F16 in GGUF?
Unquantized 16-bit floats. Original quality and the largest size. It averages about 16 bits per weight.
Should I use F16?
The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
How big is a F16 file?
F16 files on this site range from 0.0 to 2053.2 GB, depending on the model. As a rule of thumb it is about 100% of the 16-bit size.