← Back to community benchmarks
Qwen3.5-9B
Performance
32k
tokens
628.8
PP tok/s
47.8
TG tok/s
52111
TTFT (ms)
8.7
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 758.9 | 69.3 | 6.7 GB | view |
| 4k | 763.4 | 66.3 | 7.0 GB | view |
| 8k | 749.8 | 63.8 | 7.1 GB | view |
| 16k | 675.1 | 58.7 | 7.6 GB | view |
| 32k | 628.8 | 47.8 | 8.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 69.3 | 1.00× |
| 2× | 123.9 | 1.79× |
| 4× | 132.2 | 1.91× |
| 8× | 132.8 | 1.92× |