← Back to community benchmarks
Qwen3.5-4B-OptiQ
Performance
64k
tokens
529.1
PP tok/s
30.6
TG tok/s
123863
TTFT (ms)
10.3
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 711.4 | 69.0 | 4.0 GB | view |
| 4k | 775.8 | 66.0 | 4.6 GB | view |
| 8k | 767.9 | 62.1 | 5.0 GB | view |
| 16k | 730.5 | 55.2 | 5.7 GB | view |
| 32k | 647.8 | 41.8 | 7.2 GB | view |
| 64k | 529.1 | 30.6 | 10.3 GB | current |
| 128k | 370.5 | 16.5 | 16.6 GB | view |
| 195k | 274.0 | 11.8 | 23.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 69.0 | 1.00× |
| 2× | 119.3 | 1.73× |
| 4× | 151.2 | 2.19× |
| 8× | 160.5 | 2.33× |