Muse GGUF models
215 GGUF models in the Muse family, quantized by 110 uploaders. Sizes run from 105M to 820B parameters. The longest trained context is 1024K tokens.
About the Muse GGUF models
Muse is represented on ggufmodels.com by 215 GGUF models, quantized by 110 uploaders on Hugging Face. The most downloaded are Muse Glimmer 30B, Muse Glimmer 30B and Muse Glimmer 30B. Parameter counts run from 105M to 820B, and the longest trained context window is 1024K tokens.
A Q4_K_M file of a Muse model is between 0.4 to 499.6 GB, which is the quant most people start with. Most files come from mradermacher (59), MCult01 (13) and mlasli (7). The quants you will meet most often are Q4_K_M (144), Q5_K_M (101), Q8_0 (92) and Q6_K (92), where the number is how many models offer that quant.
Frequently asked questions
Which Muse GGUF should I download?
The most downloaded Muse GGUF here is Muse Glimmer 30B. 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 Muse model need?
Q4_K_M files of Muse models on this site range from 0.4 to 499.6 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 Muse GGUF files come from?
The most common quantizers here are mradermacher, MCult01 and mlasli. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.