← Back to community benchmarks

Qwen3.5-9B

M1 Pro (14c) · 16 GB · 4bit · 2026-04-16
Performance
16k
tokens
136.7
PP tok/s
25.3
TG tok/s
119854
TTFT (ms)
7.6
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 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 136.3 30.3 5.8 GB view
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 current
32k 131.1 21.2 9.1 GB view