← Back to community benchmarks
Qwen3.5-4B
Performance
1k
tokens
403.7
PP tok/s
36.2
TG tok/s
2537
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 15.1
Context
1,024
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 36.2 | 1.00× |
| 2× | 70.3 | 1.94× |
| 4× | 89.5 | 2.47× |
| 8× | 91.7 | 2.53× |