Mistral GGUF models
9355 GGUF models in the Mistral family, quantized by 2133 uploaders. Sizes run from 2M to 1050B parameters. The longest trained context is 1024K tokens.
About the Mistral GGUF models
Mistral is represented on ggufmodels.com by 9,355 GGUF models, quantized by 2,133 uploaders on Hugging Face. The most downloaded are Voxtral Mini 4B Realtime, Voxtral Small 24B and Cydonia 24B v4.3. Parameter counts run from 2M to 1050B, and the longest trained context window is 1024K tokens.
A Q4_K_M file of a Mistral model is between 0.0 to 411.4 GB, which is the quant most people start with. Most files come from mradermacher (2690), RichardErkhov (1031) and MaziyarPanahi (414). The quants you will meet most often are Q4_K_M (6915), Q5_K_M (5803), Q2_K (5665) and Q6_K (5580), where the number is how many models offer that quant.
Frequently asked questions
Which Mistral GGUF should I download?
The most downloaded Mistral GGUF here is Voxtral Mini 4B Realtime. 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 Mistral model need?
Q4_K_M files of Mistral models on this site range from 0.0 to 411.4 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 Mistral GGUF files come from?
The most common quantizers here are mradermacher, RichardErkhov and MaziyarPanahi. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.