← Back to community benchmarks
Qwen3.5-0.8B
Performance
1k
tokens
2,280
PP tok/s
110.4
TG tok/s
449
TTFT (ms)
1.8
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× | 110.4 | 1.00× |
| 2× | 109.5 | 0.99× |
| 4× | 268.9 | 2.44× |
| 8× | 321.4 | 2.91× |