← Back to community benchmarks
Qwen3.5-9B-OptiQ
Performance
4k
tokens
862.5
PP tok/s
68.9
TG tok/s
4749
TTFT (ms)
8.4
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
48 GB
GPU Cores
40
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 773.2 | 70.3 | 7.7 GB | view |
| 4k | 862.5 | 68.9 | 8.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 70.3 | 1.00× |
| 2× | 131.7 | 1.87× |
| 4× | 168.7 | 2.40× |
| 8× | 182.4 | 2.59× |