← Back to community benchmarks
Qwen3.5-9B
Performance
4k
tokens
242.1
PP tok/s
33.3
TG tok/s
16922
TTFT (ms)
11.0
Peak mem (GB)
Hardware
Chip
M1 Max (24c)
Memory
32 GB
GPU Cores
24
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 239.3 | 35.1 | 10.7 GB | view |
| 4k | 242.1 | 33.3 | 11.0 GB | current |
| 8k | 236.2 | 30.3 | 11.2 GB | view |
| 16k | 234.4 | 26.2 | 11.7 GB | view |
| 32k | 224.8 | 20.3 | 12.7 GB | view |
| 64k | 205.0 | 13.9 | 14.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 35.1 | 1.00× |
| 2× | 53.4 | 1.52× |
| 4× | 58.4 | 1.66× |
| 8× | 46.4 | 1.32× |