← Back to community benchmarks
Qwen3.5-4B
Performance
1k
tokens
407.8
PP tok/s
36.9
TG tok/s
2511
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
1,024
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 36.9 | 1.00× |
| 2× | 69.3 | 1.88× |
| 4× | 91.6 | 2.48× |
| 8× | 89.7 | 2.43× |