← Back to community benchmarks
Qwen3.5-4B
Performance
1k
tokens
262.9
PP tok/s
9.2
TG tok/s
3895
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 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× | 9.2 | 1.00× |
| 2× | 14.1 | 1.53× |
| 4× | 19.2 | 2.09× |
| 8× | 28.7 | 3.12× |