← Back to community benchmarks
Qwen3.5-9B
Performance
4k
tokens
1,641
PP tok/s
55.3
TG tok/s
2496
TTFT (ms)
7.0
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.12
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,563 | 57.5 | 6.7 GB | view |
| 4k | 1,641 | 55.3 | 7.0 GB | current |
| 8k | 1,579 | 53.8 | 7.1 GB | view |
| 16k | 1,512 | 50.1 | 7.6 GB | view |
| 32k | 1,385 | 44.0 | 8.7 GB | view |
| 64k | 1,161 | 34.9 | 10.8 GB | view |
| 128k | 838.7 | 12.5 | 15.0 GB | view |
| 195k | 640.9 | 8.7 | 19.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 57.5 | 1.00× |
| 2× | 104.8 | 1.82× |
| 4× | 141.3 | 2.46× |
| 8× | 151.5 | 2.63× |