← Back to community benchmarks
Qwen3.5-9B
Performance
16k
tokens
2,874
PP tok/s
89.7
TG tok/s
5702
TTFT (ms)
8.1
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.5.1
macOS
macOS 26.5.2
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,926 | 97.1 | 5.8 GB | view |
| 4k | 2,981 | 96.1 | 6.5 GB | view |
| 8k | 3,209 | 94.0 | 7.2 GB | view |
| 16k | 2,874 | 89.7 | 8.1 GB | current |
| 32k | 2,591 | 82.1 | 9.9 GB | view |
| 64k | 2,042 | 69.4 | 13.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 97.1 | 1.00× |
| 2× | 179.8 | 1.85× |
| 4× | 305.4 | 3.15× |