Qwen2.5-32B-Instruct-4bit
1 workload result across 1 hardware configuration.
M3 Pro (18-core GPU) + 36GB unified
| Workload | Backend | Quant | decode tok/s | prefill tok/s | TTFT | Run |
|---|---|---|---|---|---|---|
| chat-short | mlx@0.31.3 | — | 7.05tok/s | 33.41tok/s | 3,921ms | r_f4x3xaan2ay |
1 workload result across 1 hardware configuration.
| Workload | Backend | Quant | decode tok/s | prefill tok/s | TTFT | Run |
|---|---|---|---|---|---|---|
| chat-short | mlx@0.31.3 | — | 7.05tok/s | 33.41tok/s | 3,921ms | r_f4x3xaan2ay |