← Back to community benchmarks
Qwen3.5-9B
Performance
1k
tokens
443.6
PP tok/s
49.3
TG tok/s
2309
TTFT (ms)
6.7
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.7
macOS
macOS 15.3.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 443.6 | 49.3 | 6.7 GB | current |
| 4k | 449.6 | 47.1 | 7.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 49.3 | 1.00× |
| 2× | 93.0 | 1.89× |
| 4× | 100.5 | 2.04× |