← Back to community benchmarks
Qwen3.5-4B
Performance
1k
tokens
406.7
PP tok/s
38.6
TG tok/s
2518
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.9
macOS
macOS 26.3.1
Context
1,024
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 38.6 | 1.00× |
| 2× | 73.2 | 1.90× |
| 4× | 95.2 | 2.47× |
| 8× | 97.3 | 2.52× |