← Back to community benchmarks
Qwen3.5-9B
Performance
4k
tokens
103.8
PP tok/s
16.5
TG tok/s
39464
TTFT (ms)
6.4
Peak mem (GB)
Hardware
Chip
M2 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.2
macOS
macOS 15.7.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 101.5 | 17.5 | 5.7 GB | view |
| 4k | 103.8 | 16.5 | 6.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 17.5 | 1.00× |
| 2× | 24.7 | 1.41× |
| 4× | 25.4 | 1.45× |