← Back to community benchmarks
Qwen3.5-9B
Performance
1k
tokens
1,605
PP tok/s
57.8
TG tok/s
638
TTFT (ms)
6.7
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.15
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,605 | 57.8 | 6.7 GB | current |
| 4k | 1,534 | 56.1 | 7.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 57.8 | 1.00× |
| 2× | 107.0 | 1.85× |
| 4× | 143.3 | 2.48× |