Mac Studio M3 Ultra 512GB: Muse Spark Open 816B (Hugging Face test)
| GPU(s) | Apple M3 Ultra (unified) |
|---|---|
| VRAM / unified memory (GB) | 512 |
| CPU | Apple M3 Ultra |
| Motherboard | |
| RAM | |
| PSU | |
| Other | |
| Reported total cost | |
| Power |
Measured speed (generation tokens/sec)
| Model | Quant | Engine | tok/s |
|---|---|---|---|
| Muse Spark Open 816B-A42B | Q2_K (imatrix), ~304 GB | llama.cpp | 18 |
| Muse Spark Open 816B-A42B | oQ3e (3-bit), ~344 GB | MLX (oMLX / mlx-lm) | 21 |
Hugging Face's Muse Spark Open launch post (15 Oct 2026). The MLX figure used a 1,024-token prompt and 128 generated tokens (~225 tok/s prefill); prompt length for the llama.cpp figure is not stated. Meta's 816B MoE has ~42B active parameters, so it needs the full 512 GB Mac.
Source: https://huggingface.co/blog/meta-muse-spark-open
Blank fields = not stated in the source. We never estimate build data; GPU street prices above are separately sourced and dated.
Rent before you buy: try this model on a cloud GPU for a few dollars first: RunPod
Quick answers: Can Apple M3 Ultra run Muse Spark Open 816B-A42B?