← Back to community benchmarks

Qwen3.5-27B

M4 Pro (16c) · 48 GB · 4bit · 2026-04-24

Performance

8k

tokens

77.7

PP tok/s

32.5

TG tok/s

105492

TTFT (ms)

22.1

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 48 GB

GPU Cores 16

Software

oMLX v0.3.7rc1

macOS macOS 26.2

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	91.1	41.9	19.5 GB	view
4k	83.9	38.8	21.2 GB	view
8k	77.7	32.5	22.1 GB	current