← Back to community benchmarks
Qwen3.5-9B
Performance
32k
tokens
2,351
PP tok/s
56.0
TG tok/s
13936
TTFT (ms)
8.7
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.13
macOS
macOS 26.3.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 3,000 | 99.8 | 6.7 GB | view |
| 4k | 3,128 | 96.3 | 7.0 GB | view |
| 8k | 3,086 | 91.4 | 7.1 GB | view |
| 16k | 2,729 | 84.2 | 7.6 GB | view |
| 32k | 2,351 | 56.0 | 8.7 GB | current |
| 64k | 1,855 | 40.9 | 10.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 99.8 | 1.00× |
| 2× | 137.9 | 1.38× |
| 4× | 218.9 | 2.19× |
| 8× | 231.6 | 2.32× |