MLX on the M5 Max 128GB
On the M5 Max 128GB, MLX runs Nex-N2.5-mini 35B · 3B active at 4-bit at a median 133.6 tokens per second for generation, from 1 plain run (context not stated).
Speed by model on the M5 Max 128GB
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 |
|---|---|---|
| Nex-N2.5-mini 35B · 3B active 4-bit | 133.6 t/sone report, context not stated | no other engine reported |
| Qwen3 30B · 3.3B active 4-bit | 144.4 t/sone report, context not stated | no other engine reported |
| Qwen3.6 27B 8-bit | 17.2 t/sone report, 125K to 290K context | no other engine reported |
5 MLX reports on the M5 Max 128GB
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.
- Qwen3 30B · 3.3B active · MLX 4-bit affine, group 64144.4 t/s
- Qwen3 30B · 3B active130.6 t/s
- Nex-N2.5-mini 35B · 3B active · MLX-4bit133.6 t/s
- Qwen3.6 27B · Q817.2 t/s
- Qwen3.6 27B · Q8PP 160.0 t/s
Frequently asked
How fast is MLX on the M5 Max 128GB?
On the M5 Max 128GB, MLX runs Nex-N2.5-mini 35B · 3B active at 4-bit at a median 133.6 tokens per second for generation, from 1 plain run (context not stated).