← Back to community benchmarks
Qwen3.5-9B
Performance
32k
tokens
189.3
PP tok/s
19.5
TG tok/s
173137
TTFT (ms)
8.7
Peak mem (GB)
Hardware
Chip
M2 Pro (19c)
Memory
16 GB
GPU Cores
19
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 202.2 | 35.0 | 6.7 GB | view |
| 4k | 205.8 | 33.9 | 7.0 GB | view |
| 8k | 201.9 | 29.5 | 7.1 GB | view |
| 16k | 194.3 | 26.5 | 7.6 GB | view |
| 32k | 189.3 | 19.5 | 8.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 35.0 | 1.00× |
| 2× | 46.1 | 1.32× |
| 4× | 48.0 | 1.37× |