← Back to community benchmarks
Qwen3.5-9B
Performance
1k
tokens
447.9
PP tok/s
48.6
TG tok/s
2286
TTFT (ms)
6.7
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 447.9 | 48.6 | 6.7 GB | current |
| 4k | 449.0 | 46.6 | 7.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 48.6 | 1.00× |
| 2× | 92.5 | 1.90× |
| 4× | 102.7 | 2.11× |