← Back to community benchmarks
Qwen3.5-9B
Performance
1k
tokens
522.7
PP tok/s
21.1
TG tok/s
1959
TTFT (ms)
18.4
Peak mem (GB)
Hardware
Chip
M2 Max (30c)
Memory
32 GB
GPU Cores
30
Software
oMLX
v0.2.18
macOS
macOS 26.3.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 522.7 | 21.1 | 18.4 GB | current |
| 4k | 540.5 | 20.7 | 19.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 21.1 | 1.00× |
| 2× | 15.8 | 0.75× |
| 4× | 30.5 | 1.45× |