qwen2.5-72b-Instruct-4bit
1 workload result across 1 hardware configuration.
Fastest known config
16.3 decode tok/s
on M3 Ultra (60-core GPU) + 96GB unified via mlx — see full run
M3 Ultra (60-core GPU) + 96GB unified
| Workload | Backend | Quant | decode tok/s | prefill tok/s | TTFT | Run |
|---|---|---|---|---|---|---|
| chat-short | mlx@0.31.3 | — | 16.31tok/s | 23.25tok/s | 5,635ms | r_5c80gthqlh6 |