← Back to community benchmarks

Qwen3.5-9B

M4 Pro (20c) · 64 GB · 4bit · 2026-04-17
Performance
1k
tokens
418.7
PP tok/s
49.3
TG tok/s
2446
TTFT (ms)
5.8
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 418.7 49.3 5.8 GB current
4k 442.7 48.0 6.5 GB view
8k 439.2 45.1 6.9 GB view
16k 395.5 40.3 7.6 GB view
32k 365.2 34.8 9.1 GB view
64k 340.3 26.3 12.2 GB view
128k 279.9 17.8 18.5 GB view
195k 228.8 12.8 25.1 GB view