← Back to community benchmarks
Qwen3.5-9B
Performance
64k
tokens
1,158
PP tok/s
32.8
TG tok/s
56583
TTFT (ms)
13.2
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
24 GB
GPU Cores
20
Software
oMLX
v0.2.18
macOS
macOS 26.3.1
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,606 | 56.4 | 6.7 GB | view |
| 4k | 1,632 | 54.5 | 7.4 GB | view |
| 8k | 1,635 | 53.4 | 7.8 GB | view |
| 16k | 1,551 | 49.3 | 8.6 GB | view |
| 32k | 1,393 | 42.2 | 10.1 GB | view |
| 64k | 1,158 | 32.8 | 13.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 56.4 | 1.00× |
| 2× | 104.8 | 1.86× |
| 4× | 140.3 | 2.49× |
| 8× | 149.3 | 2.65× |