← Back to community benchmarks

Qwen3.6-27B-MTPLX-Optimized-Speed

M3 Ultra (60c) · 96 GB · 4bit · 2026-06-04

Performance

16k

tokens

313.0

PP tok/s

34.0

TG tok/s

52353

TTFT (ms)

19.6

Peak mem (GB)

Hardware

Chip M3 Ultra (60c)

Memory 96 GB

GPU Cores 60

Software

oMLX v0.4.1

macOS macOS 26.5

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	323.5	37.2	17.3 GB	view
16k	313.0	34.0	19.6 GB	current