← Back to community benchmarks
Qwen3.5-0.8B
Performance
1k
tokens
1,453
PP tok/s
13.3
TG tok/s
705
TTFT (ms)
3.3
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 26.3
Context
1,024
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 13.3 | 1.00× |
| 2× | 14.1 | 1.06× |
| 4× | 24.4 | 1.83× |
| 8× | 37.7 | 2.83× |