← Back to community benchmarks
Qwen3.5-9B
Performance
8k
tokens
436.4
PP tok/s
43.5
TG tok/s
18774
TTFT (ms)
7.1
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.6
macOS
macOS 26.2
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 444.4 | 49.2 | 6.7 GB | view |
| 4k | 447.5 | 47.0 | 7.0 GB | view |
| 8k | 436.4 | 43.5 | 7.1 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 49.2 | 1.00× |
| 2× | 91.2 | 1.85× |
| 4× | 98.7 | 2.01× |
| 8× | 103.3 | 2.10× |