← Back to community benchmarks
Qwen3.5-9Blm
Performance
4k
tokens
180.4
PP tok/s
33.0
TG tok/s
22710
TTFT (ms)
6.3
Peak mem (GB)
Hardware
Chip
M2 Pro (16c)
Memory
16 GB
GPU Cores
16
Software
oMLX
v0.3.5
macOS
macOS 26.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 173.1 | 35.1 | 5.6 GB | view |
| 4k | 180.4 | 33.0 | 6.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 35.1 | 1.00× |
| 2× | 37.6 | 1.07× |
| 4× | 38.9 | 1.11× |