← Back to community benchmarks
Qwen3.5-9B
Performance
1k
tokens
353.1
PP tok/s
27.9
TG tok/s
2900
TTFT (ms)
10.7
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
24 GB
GPU Cores
16
Software
oMLX
v0.2.10
macOS
macOS 26.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 353.1 | 27.9 | 10.7 GB | current |
| 4k | 363.2 | 27.5 | 11.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 27.9 | 1.00× |
| 2× | 52.1 | 1.87× |
| 4× | 59.9 | 2.15× |
| 8× | 62.5 | 2.24× |