← Back to community benchmarks
Qwen3.5-9B
Performance
1k
tokens
169.5
PP tok/s
30.5
TG tok/s
6042
TTFT (ms)
6.7
Peak mem (GB)
Hardware
Chip
M2 Pro (16c)
Memory
32 GB
GPU Cores
16
Software
oMLX
v0.2.7
macOS
macOS 26.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 169.5 | 30.5 | 6.7 GB | current |
| 4k | 170.1 | 31.9 | 7.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 30.5 | 1.00× |
| 2× | 38.7 | 1.27× |
| 4× | 42.3 | 1.39× |