← Back to community benchmarks
Qwen3.5-9B
Performance
4k
tokens
740.9
PP tok/s
6.2
TG tok/s
5529
TTFT (ms)
23.0
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 596.8 | 6.2 | 22.8 GB | view |
| 4k | 740.9 | 6.2 | 23.0 GB | current |
| 8k | 766.5 | 6.1 | 23.3 GB | view |
| 16k | 750.4 | 6.0 | 23.7 GB | view |
| 32k | 698.5 | 5.8 | 24.7 GB | view |
| 64k | 590.1 | 5.5 | 27.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 6.2 | 1.00× |
| 2× | 10.6 | 1.71× |
| 4× | 21.2 | 3.42× |
| 8× | 42.0 | 6.77× |