← Back to community benchmarks
Qwen3.5-0.8B
Performance
1k
tokens
3,481
PP tok/s
47.9
TG tok/s
294
TTFT (ms)
3.5
Peak mem (GB)
Hardware
Chip
M2 Max (38c)
Memory
96 GB
GPU Cores
38
Software
oMLX
v0.2.7
macOS
macOS 15.6.1
Context
1,024
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 47.9 | 1.00× |
| 2× | 62.2 | 1.30× |
| 4× | 101.4 | 2.12× |
| 8× | 71.1 | 1.48× |