This is a 3-bit exl2 (Exllamav2) conversion of MistralAI's Mixtral-8x7B-Instruct-v0.1
It takes about 17GB on disk, so it should load on consumer cards with 24GB of VRAM.
- More on ExLlamav2 -> https://github.com/turboderp/exllamav2 ( works with Oobabooga's textgen web ui )
- Original Model -> https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1 ( Original files are ~87GB on disk )
- Downloads last month
- 4
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support