← Back to community benchmarks

Qwen3.5-2B-OptiQ

M2 Max (38c) · 64 GB · 4bit · 2026-04-16
Performance
32k
tokens
1,619
PP tok/s
89.9
TG tok/s
20237
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip M2 Max (38c)
Memory 64 GB
GPU Cores 38
Software
oMLX v0.3.5
macOS macOS 15.7.5
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,281 162.5 2.4 GB view
4k 1,666 148.5 2.7 GB view
8k 1,739 135.5 2.8 GB view
16k 1,719 116.2 3.2 GB view
32k 1,619 89.9 3.9 GB current