← Back to community benchmarks
Qwen3.5-9B
Performance
1k
tokens
127.6
PP tok/s
12.3
TG tok/s
8027
TTFT (ms)
10.7
Peak mem (GB)
Hardware
Chip
M2 Pro (16c)
Memory
32 GB
GPU Cores
16
Software
oMLX
v0.2.6
macOS
macOS 15.7.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 127.6 | 12.3 | 10.7 GB | current |
| 4k | 132.0 | 12.0 | 11.0 GB | view |
| 8k | 130.7 | 11.5 | 11.2 GB | view |
| 16k | 127.5 | 10.6 | 11.7 GB | view |
| 32k | 90.4 | 8.6 | 12.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 12.3 | 1.00× |
| 2× | 18.4 | 1.50× |
| 4× | 24.0 | 1.95× |
| 8× | 25.1 | 2.04× |