← Back to community benchmarks
Qwen3.5-9B
Performance
8k
tokens
1,879
PP tok/s
6.2
TG tok/s
4361
TTFT (ms)
23.3
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.9
macOS
macOS 26.3.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 988.2 | 6.2 | 22.8 GB | view |
| 4k | 1,484 | 6.2 | 23.0 GB | view |
| 8k | 1,879 | 6.2 | 23.3 GB | current |
| 16k | 1,821 | 5.9 | 23.7 GB | view |
| 32k | 1,592 | 5.8 | 24.7 GB | view |
| 64k | 1,243 | 5.8 | 27.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 6.2 | 1.00× |
| 2× | 12.2 | 1.97× |
| 4× | 24.2 | 3.90× |
| 8× | 47.3 | 7.63× |