← Back to community benchmarks
Qwen3.5-4B
Performance
1k
tokens
656.0
PP tok/s
82.1
TG tok/s
1561
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 | 656.0 | 82.1 | 4.0 GB | current |
| 4k | 653.6 | 77.3 | 4.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 82.1 | 1.00× |
| 2× | 133.0 | 1.62× |
| 4× | 147.8 | 1.80× |
| 8× | 152.7 | 1.86× |