← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M5 Max (40c) · 128 GB · 4bit · 2026-05-21

Performance

8k

tokens

882.9

PP tok/s

43.7

TG tok/s

9278

TTFT (ms)

18.8

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.9rc1

macOS macOS 26.4

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
8k	882.9	43.7	18.8 GB	current
16k	774.6	40.1	20.7 GB	view
32k	671.3	36.1	23.7 GB	view
64k	547.5	28.6	29.8 GB	view
128k	372.3	21.5	42.1 GB	view