← Back to community benchmarks
Qwen3.5-9B
Performance
8k
tokens
174.3
PP tok/s
32.4
TG tok/s
46996
TTFT (ms)
7.1
Peak mem (GB)
Hardware
Chip
M2 Pro (16c)
Memory
16 GB
GPU Cores
16
Software
oMLX
v0.2.12
macOS
macOS 26.3.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 176.0 | 36.1 | 6.7 GB | view |
| 4k | 176.1 | 34.2 | 7.0 GB | view |
| 8k | 174.3 | 32.4 | 7.1 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 36.1 | 1.00× |
| 2× | 40.4 | 1.12× |
| 4× | 41.9 | 1.16× |