← Back to community benchmarks
Qwen3.5-9B-OptiQ
Performance
1k
tokens
681.3
PP tok/s
22.6
TG tok/s
1503
TTFT (ms)
6.7
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.19
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 681.3 | 22.6 | 6.7 GB | current |
| 4k | 722.3 | 22.8 | 7.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 22.6 | 1.00× |
| 2× | 48.4 | 2.14× |
| 4× | 68.9 | 3.05× |