Model GGUF models
1010 GGUF models in the Model family, quantized by 754 uploaders. Sizes run from 13M to 69B parameters. The longest trained context is 1024K tokens.
About the Model GGUF models
Model is represented on ggufmodels.com by 1,010 GGUF models, quantized by 754 uploaders on Hugging Face. The most downloaded are model 007 70B, Model Compilation and PJ 7B MODEL FINAL. Parameter counts run from 13M to 69B, and the longest trained context window is 1024K tokens.
A Q4_K_M file of a Model model is between 0.0 to 41.4 GB, which is the quant most people start with. Most files come from RichardErkhov (37), LucileFavero (26) and mradermacher (18). The quants you will meet most often are Q8_0 (543), Q4_K_M (498), Q5_K_M (229) and F16 (228), where the number is how many models offer that quant.
Frequently asked questions
Which Model GGUF should I download?
The most downloaded Model GGUF here is model 007 70B. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.
How much VRAM does a Model model need?
Q4_K_M files of Model models on this site range from 0.0 to 41.4 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.
Where do Model GGUF files come from?
The most common quantizers here are RichardErkhov, LucileFavero and mradermacher. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.