← Back to community benchmarks
Qwen3.5-9B-OptiQ
Performance
1k
tokens
267.2
PP tok/s
47.3
TG tok/s
3832
TTFT (ms)
6.8
Peak mem (GB)
Hardware
Chip
M2 Max (30c)
Memory
64 GB
GPU Cores
30
Software
oMLX
v0.2.7
macOS
macOS 15.7.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 267.2 | 47.3 | 6.8 GB | current |
| 4k | 243.9 | 48.3 | 7.0 GB | view |
| 8k | 267.9 | 48.6 | 7.2 GB | view |
| 16k | 281.9 | 44.4 | 7.7 GB | view |
| 32k | 259.2 | 33.7 | 8.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 47.3 | 1.00× |
| 2× | 101.6 | 2.15× |
| 4× | 207.5 | 4.39× |