meta-models · First MLX build 15 Oct 2026
Muse-Spark-Open-816B-A42B
MLX
TextVision muse-model-license
A 822B parameter vision and text model from meta-models, with 4 MLX builds, from 3-bit to 4-bit.
- Parameters
- 822B From Hugging Face
- Quantisation
- 4-bit Muse-Spark-Open-816B-A42B-4bit
- Memory needed
- 598 GB Estimate, unified memory
- Download
- 533 GB Weights, estimated
- Downloads
- 9.6K This build, last 30 days
- Task
- Vision and text Text, Vision
- MLX builds
- 4 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 598 GB at 4-bit
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · mlx-vlm$ pip install -U mlx-vlm
$ python -m mlx_vlm.generate --model mlx-community/Muse-Spark-Open-816B-A42B-4bit --image photo.jpg --prompt "Describe this image"MLX builds
4 on mlx-community| Muse-Spark-Open-816B-A42B-oQ3e | 3-bit | 366 GB | 411 GB | 2.5K |
|---|---|---|---|---|
| Muse-Spark-Open-816B-A42B-3bit | 3-bit | 436 GB | 490 GB | 1.9K |
| Muse-Spark-Open-816B-A42B-oQ4e | 4-bit | 468 GB | 525 GB | 1.9K |
| Muse-Spark-Open-816B-A42B-4bit | 4-bit | 533 GB | 598 GB | 9.6K |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.