← Back to community benchmarks
Qwen3.5-9B-OptiQ
Performance
1k
tokens
343.3
PP tok/s
45.2
TG tok/s
2983
TTFT (ms)
6.8
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
24 GB
GPU Cores
16
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 343.3 | 45.2 | 6.8 GB | current |
| 4k | 357.8 | 41.7 | 7.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 45.2 | 1.00× |
| 2× | 68.7 | 1.52× |
| 4× | 78.7 | 1.74× |
| 8× | 83.3 | 1.84× |