← Back to community benchmarks
Qwen3.5-9B
Performance
32k
tokens
385.7
PP tok/s
35.2
TG tok/s
84961
TTFT (ms)
8.7
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 445.3 | 49.2 | 6.7 GB | view |
| 4k | 451.2 | 47.4 | 7.0 GB | view |
| 8k | 442.6 | 45.5 | 7.1 GB | view |
| 16k | 410.5 | 42.0 | 7.6 GB | view |
| 32k | 385.7 | 35.2 | 8.7 GB | current |
| 64k | 354.8 | 28.0 | 10.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 49.2 | 1.00× |
| 2× | 92.3 | 1.88× |
| 4× | 101.7 | 2.07× |
| 8× | 106.5 | 2.16× |