Qwen2.5-Coder-32B-Instruct-4bit
2 workload results across 2 hardware configurations.
Fastest known config
34.5 decode tok/s
on M3 Ultra (60-core GPU) + 96GB unified via mlx — see full run
M3 Pro (18-core GPU) + 36GB unified
| Workload | Backend | Quant | decode tok/s | prefill tok/s | TTFT | Run |
|---|---|---|---|---|---|---|
| chat-short | mlx@0.31.3 | — | no data | no data | no data | r_v-6671pyyqs |
M3 Ultra (60-core GPU) + 96GB unified
| Workload | Backend | Quant | decode tok/s | prefill tok/s | TTFT | Run |
|---|---|---|---|---|---|---|
| chat-short | mlx@0.31.3 | — | 34.48tok/s | 144.1tok/s | 909ms | r_721b4bls_oq |