← Back to community benchmarks
Qwen3.5-9B
Performance
1k
tokens
439.6
PP tok/s
49.4
TG tok/s
2329
TTFT (ms)
6.7
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 439.6 | 49.4 | 6.7 GB | current |
| 4k | 432.3 | 46.6 | 7.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 49.4 | 1.00× |
| 2× | 89.6 | 1.81× |
| 4× | 101.1 | 2.05× |