← Back to community benchmarks

Qwen3.6-27B-oQ8-mtp

M5 Max (40c) · 128 GB · 8bit · 2026-05-25

Performance

32k

tokens

371.1

PP tok/s

10.1

TG tok/s

88305

TTFT (ms)

35.3

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.10

macOS macOS 26.4.1

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	299.9	11.8	28.3 GB	view
4k	401.8	11.8	29.8 GB	view
8k	418.8	11.8	30.8 GB	view
16k	410.8	11.3	32.3 GB	view
32k	371.1	10.1	35.3 GB	current
64k	289.6	8.4	41.4 GB	view