← Back to community benchmarks
Qwen3.5-9B
Performance
1k
tokens
170.2
PP tok/s
34.3
TG tok/s
6018
TTFT (ms)
6.7
Peak mem (GB)
Hardware
Chip
M2 Pro (16c)
Memory
16 GB
GPU Cores
16
Software
oMLX
v0.2.6
macOS
macOS 26.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 170.2 | 34.3 | 6.7 GB | current |
| 4k | 170.4 | 32.0 | 7.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 34.3 | 1.00× |
| 2× | 39.6 | 1.15× |
| 4× | 41.8 | 1.22× |