← Back to community benchmarks
Qwen3.5-9B
Performance
1k
tokens
1,447
PP tok/s
31.3
TG tok/s
708
TTFT (ms)
10.7
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.13
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,447 | 31.3 | 10.7 GB | current |
| 4k | 1,546 | 30.4 | 11.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 31.3 | 1.00× |
| 2× | 59.8 | 1.91× |
| 4× | 89.5 | 2.86× |