← Back to community benchmarks
Qwen3.5-9B
Performance
1k
tokens
341.6
PP tok/s
27.7
TG tok/s
2997
TTFT (ms)
6.7
Peak mem (GB)
Hardware
Chip
M3 Pro (18c)
Memory
18 GB
GPU Cores
18
Software
oMLX
v0.2.11
macOS
macOS 26.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 341.6 | 27.7 | 6.7 GB | current |
| 4k | 350.5 | 26.9 | 7.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 27.7 | 1.00× |
| 2× | 54.4 | 1.96× |
| 4× | 80.2 | 2.90× |
| 8× | 81.0 | 2.92× |