← Back to community benchmarks

Qwen3.5-27B-Architect-Polaris-Heretic-mxfp4

M5 Max (40c) · 64 GB · 4bit · 2026-04-18

Performance

32k

tokens

1,429

PP tok/s

29.5

TG tok/s

22927

TTFT (ms)

24.2

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.6

macOS macOS 26.4.1

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	500.6	32.9	19.2 GB	view
16k	1,355	32.8	22.9 GB	view
32k	1,429	29.5	24.2 GB	current