← Back to community benchmarks
Qwen3.5-9B
Performance
195k
tokens
987.3
PP tok/s
24.8
TG tok/s
202576
TTFT (ms)
26.2
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.24
macOS
macOS 26.3.2
Context
200,000
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,833 | 81.5 | 6.7 GB | view |
| 4k | 2,714 | 78.6 | 7.4 GB | view |
| 8k | 3,155 | 73.1 | 7.8 GB | view |
| 16k | 2,864 | 69.1 | 8.6 GB | view |
| 32k | 2,551 | 61.4 | 10.1 GB | view |
| 64k | 1,974 | 41.5 | 13.2 GB | view |
| 128k | 1,349 | 28.1 | 19.6 GB | view |
| 195k | 987.3 | 24.8 | 26.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 81.5 | 1.00× |
| 2× | 136.2 | 1.67× |
| 4× | 185.6 | 2.28× |
| 8× | 207.0 | 2.54× |