← Back to community benchmarks
Qwen3.5-0.8B
Performance
1k
tokens
4,453
PP tok/s
209.6
TG tok/s
230
TTFT (ms)
2.0
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.6
macOS
macOS 26.1
Context
1,024
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 209.6 | 1.00× |
| 2× | 208.6 | 1.00× |
| 4× | 244.3 | 1.17× |
| 8× | 516.0 | 2.46× |