← Back to community benchmarks
Qwen3.5-9B
Performance
1k
tokens
341.7
PP tok/s
14.7
TG tok/s
2996
TTFT (ms)
10.7
Peak mem (GB)
Hardware
Chip
M3 Pro (18c)
Memory
36 GB
GPU Cores
18
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 | 341.7 | 14.7 | 10.7 GB | current |
| 4k | 341.1 | 14.6 | 11.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 14.7 | 1.00× |
| 2× | 30.2 | 2.05× |
| 4× | 56.7 | 3.86× |