← Back to community benchmarks
Qwen3.5-4B
Performance
4k
tokens
616.1
PP tok/s
44.8
TG tok/s
6648
TTFT (ms)
4.2
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
24 GB
GPU Cores
20
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 595.3 | 28.1 | 4.0 GB | view |
| 4k | 616.1 | 44.8 | 4.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 28.1 | 1.00× |
| 2× | 47.3 | 1.68× |
| 4× | 77.5 | 2.76× |