← Back to community benchmarks

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

M5 Max (40c) · 128 GB · 6bit · 2026-06-14

Performance

1k

tokens

757.9

PP tok/s

29.1

TG tok/s

1351

TTFT (ms)

19.1

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.4.4rc1

macOS macOS 26.5.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	757.9	29.1	19.1 GB	current
4k	905.5	28.0	20.5 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	29.1	1.00×
2×	49.3	1.69×
4×	109.2	3.75×