← Back to community benchmarks
Qwen3.5-9B-MTPLX-Optimized-Speed
Performance
32k
tokens
517.4
PP tok/s
15.3
TG tok/s
63329
TTFT (ms)
11.7
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.5.1
macOS
macOS 26.5.2
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 661.9 | 18.1 | 7.8 GB | view |
| 4k | 671.3 | 17.7 | 8.3 GB | view |
| 8k | 657.1 | 17.4 | 8.8 GB | view |
| 16k | 615.0 | 16.8 | 9.9 GB | view |
| 32k | 517.4 | 15.3 | 11.7 GB | current |
| 64k | 408.5 | 12.9 | 14.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 18.1 | 1.00× |
| 2× | 34.6 | 1.91× |
| 4× | 55.1 | 3.04× |