← Back to community benchmarks
Qwen3.5-9B
Performance
1k
tokens
237.7
PP tok/s
46.7
TG tok/s
4308
TTFT (ms)
6.7
Peak mem (GB)
Hardware
Chip
M1 Max (24c)
Memory
32 GB
GPU Cores
24
Software
oMLX
v0.2.8
macOS
macOS 26.3.1
Context
1,024
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 46.7 | 1.00× |
| 2× | 52.4 | 1.12× |
| 4× | 56.1 | 1.20× |
| 8× | 46.3 | 0.99× |