← Back to community benchmarks

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

M5 Max (40c) · 128 GB · 4bit · 2026-06-19

Performance

16k

tokens

828.6

PP tok/s

31.6

TG tok/s

19774

TTFT (ms)

19.6

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.4.4

macOS macOS 26.5.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	915.1	33.6	17.3 GB	view
16k	828.6	31.6	19.6 GB	current