MLX on the M3 Ultra 96GB
On the M3 Ultra 96GB, MLX runs gpt-oss 117B · 5.1B active at 4-bit at a median 73.0 tokens per second for generation, from 1 plain run (context not stated).
Speed by model on the M3 Ultra 96GB
Plain runs only: one device, one request, no speculative decoding, the whole model in memory. Each row is one model size at one bit class, with the other engines' plain runs of the same model on this card beside it. Context length and build still differ between runs, and each side shows its own.
| Model | MLX | Other engines |
|---|---|---|
| gpt-oss 117B · 5.1B active 4-bit | 73.0 t/sone report, context not stated | no other engine reported |
| Qwen3.5 35B · 3B active 4-bit | 109.7 t/sone report, context not stated | no other engine reported |
3 MLX reports on the M3 Ultra 96GB
Newest first. A run on several cards, with speculative decoding, with part of the model in system RAM or with batched requests says so, since each describes a different setup.
- gpt-oss 117B · 5.1B active · MXFP473.0 t/s
- Qwen3-Next 80B · 3B active · 4-bit49.1 t/s
- Qwen3.5 35B · 3B active · 4-bit109.7 t/s
Frequently asked
How fast is MLX on the M3 Ultra 96GB?
On the M3 Ultra 96GB, MLX runs gpt-oss 117B · 5.1B active at 4-bit at a median 73.0 tokens per second for generation, from 1 plain run (context not stated).