Muse-Spark-Open-816B-A42B

by meta-models

Task
Vision-language (image + text to text)
Category
Image
License
Custom (other)
Commercial use
Check the license
The license isn't a standard one; read the model card on Hugging Face before using it commercially.
Size
About 816 billion parameters
Memory to load
~1959 GB (estimate)
Format
FP16
Runs on
GPU
Access
Gated: accept the publisher's terms on Hugging Face
Downloads (last 30 days)
2.1K
Likes
572
Last updated
October 15, 2026

How to run it

These are full-precision weights, usually loaded with Hugging Face Transformers or Diffusers on a GPU.

Plan for roughly 1959 GB of memory to load it (our estimate from its size and format).

Downloads are gated: accept the publisher's terms on Hugging Face first.

The model card on Hugging Face has the exact usage code.

Related vision-language (image + text to text) models

Data from Hugging Face's public API, last checked October 19, 2026. Downloads are Hugging Face's count for the last 30 days.