← Back to community benchmarks
Qwen3.5-9B
Performance
1k
tokens
287.5
PP tok/s
57.4
TG tok/s
3561
TTFT (ms)
6.7
Peak mem (GB)
Hardware
Chip
M2 Max (30c)
Memory
64 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 | 287.5 | 57.4 | 6.7 GB | current |
| 4k | 320.1 | 57.7 | 7.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 57.4 | 1.00× |
| 2× | 70.5 | 1.23× |
| 4× | 75.6 | 1.32× |