Q8_0 GGUF models
8-bit quant. Near-lossless, at roughly twice the size of a 4-bit quant. 111847 models have a Q8_0 file. Sizes run from 1M to 2780B parameters. The longest trained context is 4194304K tokens.
What is Q8_0?
8-bit quant. Near-lossless, at roughly twice the size of a 4-bit quant. On average it stores about 8.5 bits per weight, so a Q8_0 file is roughly 53% of the size of the same model in 16-bit. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
111,847 models have a Q8_0 file on ggufmodels.com, and those files range from 0.0 to 2955.0 GB. The most downloaded are YuE2 audio tokenizer, the v9 head of Mothersuperior, on MERT-v2-FullSong, Qwen3.8-27B and Ornith-1.5-9B. For a longer explanation of every quant type, read GGUF quantization explained.
Frequently asked questions
What is Q8_0 in GGUF?
8-bit quant. Near-lossless, at roughly twice the size of a 4-bit quant. It averages about 8.5 bits per weight.
Should I use Q8_0?
Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
How big is a Q8_0 file?
Q8_0 files on this site range from 0.0 to 2955.0 GB, depending on the model. As a rule of thumb it is about 53% of the 16-bit size.