← Back to community benchmarks

Qwen3.5-27B-Claude-4.6-Opus-Distilled

M4 Max (40c) · 64 GB · 4bit · 2026-03-14

Performance

1k

tokens

225.0

PP tok/s

29.2

TG tok/s

4551

TTFT (ms)

15.8

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.2.11

macOS macOS 26.3.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	225.0	29.2	15.8 GB	current
4k	240.2	28.1	16.1 GB	view
8k	236.4	26.9	16.6 GB	view
16k	227.7	24.3	17.5 GB	view