← Back to community benchmarks
Qwen3.5-9B
Performance
1k
tokens
566.0
PP tok/s
49.3
TG tok/s
1809
TTFT (ms)
6.7
Peak mem (GB)
Hardware
Chip
M3 Max (30c)
Memory
36 GB
GPU Cores
30
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 566.0 | 49.3 | 6.7 GB | current |
| 4k | 573.6 | 50.9 | 7.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 49.3 | 1.00× |
| 2× | 97.7 | 1.98× |
| 4× | 96.3 | 1.95× |