4-bit Open on Hugging Face
Parameters
822B
Weights (est.)
≈ 468 GB
Mac memory (est.)
> 512 GB
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-vlm on an Apple silicon Mac:
pip install mlx-vlmpython -m mlx_vlm.generate --model mlx-community/Muse-Spark-Open-816B-A42B-oQ4e --image photo.jpg --prompt "Describe this image"
Details
- Base model
- meta-models/Muse-Spark-Open-816B-A42B (quantized)
- Vendor
- meta-models
- Task
- Vision + text
- Quantisation
- 4-bit
- Licence
- muse-model-license
- Downloads
- 1.9K in the last 30 days · 1.9K all time · 6 likes
- Published
- 2026-10-15 · updated 2026-10-16 (26d ago)
- Tags
- muse_spark, quantized, muse, muse-spark
Other MLX builds of meta-models/Muse-Spark-Open-816B-A42B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Muse-Spark-Open-816B-A42B-oQ3e | 3-bit | ≈ 366 GB | 512 GB+ | 2.5K |
| Muse-Spark-Open-816B-A42B-3bit | 3-bit | ≈ 436 GB | 512 GB+ | 1.9K |
| Muse-Spark-Open-816B-A42B-oQ4e (this one) | 4-bit | ≈ 468 GB | > 512 GB | 1.9K |
| Muse-Spark-Open-816B-A42B-4bit | 4-bit | ≈ 533 GB | > 512 GB | 9.6K |