← Back to community benchmarks

Qwen3.5-2B

M2 Max (30c) · 32 GB · 4bit · 2026-07-16

Performance

64k

tokens

894.6

PP tok/s

86.4

TG tok/s

73261

TTFT (ms)

2.9

Peak mem (GB)

Hardware

Chip M2 Max (30c)

Memory 32 GB

GPU Cores 30

Software

oMLX v0.5.1

macOS macOS 26.6

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
64k	894.6	86.4	2.9 GB	current
128k	607.4	57.3	4.2 GB	view