← Back to community benchmarks
Qwen3.5-9B-OptiQ
Performance
1k
tokens
324.2
PP tok/s
25.9
TG tok/s
3158
TTFT (ms)
6.8
Peak mem (GB)
Hardware
Chip
M3 Pro (18c)
Memory
36 GB
GPU Cores
18
Software
oMLX
v0.2.10
macOS
macOS 26.0.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 324.2 | 25.9 | 6.8 GB | current |
| 4k | 344.2 | 25.2 | 7.0 GB | view |
| 8k | 341.9 | 24.2 | 7.2 GB | view |
| 16k | 331.5 | 22.5 | 7.7 GB | view |
| 32k | 309.9 | 20.0 | 8.8 GB | view |
| 64k | 269.3 | 15.4 | 10.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 25.9 | 1.00× |
| 2× | 51.2 | 1.98× |
| 4× | 102.5 | 3.96× |
| 8× | 204.8 | 7.91× |