← Back to community benchmarks
Qwen3.5-9B
Performance
1k
tokens
203.5
PP tok/s
35.6
TG tok/s
5033
TTFT (ms)
6.7
Peak mem (GB)
Hardware
Chip
M2 Pro (19c)
Memory
16 GB
GPU Cores
19
Software
oMLX
v0.2.7
macOS
macOS 26.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 203.5 | 35.6 | 6.7 GB | current |
| 4k | 207.3 | 33.8 | 7.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 35.6 | 1.00× |
| 2× | 46.7 | 1.31× |
| 4× | 46.3 | 1.30× |