Downloads · 30 days
4
6% of all-time downloads
Mixtral-8x7B-v0.1-W8A16
Lynawa/Mixtral-8x7B-v0.1-W8A16
Mixtral-8x7B-v0.1-W8A16 is a machine learning model from Lynawa. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
This model is an INT8 weight-only quantized version of Mixtral-8x7B-v0.1.
All-time downloads
64
Public
Parameters
46.7B
47 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors47 GB · 100%
Parameter types
How the weights are stored.
I846.4B · 99%
Base models
Model card
From the Hugging Face model README
Mixtral-8x7B-v0.1-W8A16
This model is an INT8 weight-only quantized version of Mixtral-8x7B-v0.1.
- Type
- mixtral
- License
- mit
- Created
- Aug 13, 2025
- Updated
- Aug 13, 2025