← Back to community benchmarks
Qwen3.5-4B
Performance
1k
tokens
372.6
PP tok/s
31.0
TG tok/s
2749
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
1,024
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 31.0 | 1.00× |
| 2× | 57.1 | 1.84× |
| 4× | 80.5 | 2.60× |
| 8× | 85.3 | 2.75× |