← Back to community benchmarks
Qwen3.5-9B
Performance
1k
tokens
363.1
PP tok/s
49.8
TG tok/s
2820
TTFT (ms)
6.7
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
48 GB
GPU Cores
16
Software
oMLX
v0.2.9
macOS
macOS 26.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 363.1 | 49.8 | 6.7 GB | current |
| 4k | 364.7 | 47.9 | 7.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 49.8 | 1.00× |
| 2× | 79.7 | 1.60× |
| 4× | 84.4 | 1.69× |
| 8× | 85.8 | 1.72× |