← Back to community benchmarks
Qwen3.5-9B
Performance
4k
tokens
326.5
PP tok/s
58.3
TG tok/s
12547
TTFT (ms)
7.0
Peak mem (GB)
Hardware
Chip
M2 Max (30c)
Memory
32 GB
GPU Cores
30
Software
oMLX
v0.2.6
macOS
macOS 26.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 325.0 | 61.0 | 6.7 GB | view |
| 4k | 326.5 | 58.3 | 7.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 61.0 | 1.00× |
| 2× | 71.5 | 1.17× |
| 4× | 76.7 | 1.26× |