← Back to community benchmarks
Qwen3.5-9B
Performance
4k
tokens
1,524
PP tok/s
55.5
TG tok/s
2689
TTFT (ms)
7.0
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.12
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,515 | 57.6 | 6.7 GB | view |
| 4k | 1,524 | 55.5 | 7.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 57.6 | 1.00× |
| 2× | 105.9 | 1.84× |
| 4× | 140.0 | 2.43× |
| 8× | 150.6 | 2.61× |