← Back to community benchmarks

Qwen3.5-9B

M1 Pro (14c) · 16 GB · 4bit · 2026-04-16
Performance
1k
tokens
136.3
PP tok/s
30.3
TG tok/s
7511
TTFT (ms)
5.8
Peak mem (GB)
Hardware
Chip M1 Pro (14c)
Memory 16 GB
GPU Cores 14
Software
oMLX v0.3.5
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 136.3 30.3 5.8 GB current
4k 140.0 29.1 6.5 GB view
8k 139.3 27.9 6.9 GB view
16k 136.7 25.3 7.6 GB view
32k 131.1 21.2 9.1 GB view