← Back to community benchmarks
Qwen3.5-0.8B
Performance
1k
tokens
506.6
PP tok/s
7.9
TG tok/s
2021
TTFT (ms)
3.3
Peak mem (GB)
Hardware
Chip
M3 (10c)
Memory
24 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× | 7.9 | 1.00× |
| 2× | 7.7 | 0.97× |
| 4× | 18.9 | 2.39× |
| 8× | 24.4 | 3.09× |