← Back to community benchmarks

Qwen3.5-9B-PARO

M4 Pro (20c) · 48 GB · 4bit · 2026-05-18
Performance
1k
tokens
433.7
PP tok/s
46.6
TG tok/s
2361
TTFT (ms)
5.7
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 48 GB
GPU Cores 20
Software
oMLX v0.3.9.dev2
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 433.7 46.6 5.7 GB current
4k 447.1 47.9 6.3 GB view
8k 456.4 46.5 6.7 GB view
16k 441.8 43.1 7.7 GB view
32k 413.6 38.1 9.4 GB view
64k 363.4 30.8 13.0 GB view
Batching Results
Batch Size TG tok/s Speedup
46.6 1.00×
86.7 1.86×
99.2 2.13×
378.1 8.11×