← Back to community benchmarks
Qwen3.5-9B-OptiQ
Performance
1k
tokens
322.9
PP tok/s
25.1
TG tok/s
3171
TTFT (ms)
6.8
Peak mem (GB)
Hardware
Chip
M3 Pro (18c)
Memory
18 GB
GPU Cores
18
Software
oMLX
v0.2.17
macOS
macOS 26.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 322.9 | 25.1 | 6.8 GB | current |
| 4k | 335.4 | 24.4 | 7.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 25.1 | 1.00× |
| 2× | 50.2 | 2.00× |
| 4× | 101.3 | 4.04× |
| 8× | 202.5 | 8.07× |