← Back to community benchmarks
Qwen3.5-4B
Performance
1k
tokens
357.9
PP tok/s
34.5
TG tok/s
2861
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× | 34.5 | 1.00× |
| 2× | 65.4 | 1.90× |
| 4× | 88.8 | 2.57× |
| 8× | 85.4 | 2.48× |