← Back to community benchmarks

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

M5 Max (40c) · 128 GB · 4bit · 2026-05-14

Performance

128k

tokens

402.4

PP tok/s

12.6

TG tok/s

325735

TTFT (ms)

49.6

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.8

macOS macOS 26.5

Context 131,072

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
64k	599.7	15.7	39.2 GB	view
128k	402.4	12.6	49.6 GB	current