← Back to community benchmarks
Qwen3.5-9B
Performance
1k
tokens
715.0
PP tok/s
69.4
TG tok/s
1432
TTFT (ms)
6.7
Peak mem (GB)
Hardware
Chip
M4 Max (32c)
Memory
36 GB
GPU Cores
32
Software
oMLX
v0.2.10
macOS
macOS 26.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 715.0 | 69.4 | 6.7 GB | current |
| 4k | 719.0 | 66.3 | 7.0 GB | view |
| 8k | 709.1 | 63.7 | 7.1 GB | view |
| 16k | 685.1 | 58.6 | 7.6 GB | view |
| 32k | 641.0 | 51.0 | 8.7 GB | view |
| 64k | 566.2 | 35.6 | 10.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 69.4 | 1.00× |
| 2× | 133.1 | 1.92× |
| 4× | 156.2 | 2.25× |
| 8× | 166.9 | 2.40× |