← Back to community benchmarks
Qwen3.5-4B
Performance
1k
tokens
655.6
PP tok/s
82.6
TG tok/s
1562
TTFT (ms)
4.0
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
24 GB
GPU Cores
16
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 655.6 | 82.6 | 4.0 GB | current |
| 4k | 652.4 | 77.6 | 4.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 82.6 | 1.00× |
| 2× | 132.9 | 1.61× |
| 4× | 146.9 | 1.78× |
| 8× | 152.9 | 1.85× |