← Back to community benchmarks

Qwen3.6-27B-Holodeck-Qwopus-GLM-qx64-hi

M5 Max (40c) · 128 GB · 6bit · 2026-04-30

Performance

4k

tokens

235.8

PP tok/s

87.4

TG tok/s

17372

TTFT (ms)

24.6

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.8rc1

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	247.4	107.7	22.8 GB	view
4k	235.8	87.4	24.6 GB	current
8k	209.5	60.9	25.0 GB	view
16k	169.1	31.3	25.9 GB	view
32k	94.1	20.1	27.8 GB	view