← Back to community benchmarks

Qwen3.6-27B-oQ8-mtp

M3 Ultra (80c) · 512 GB · 8bit · 2026-05-20

Performance

1k

tokens

387.3

PP tok/s

32.6

TG tok/s

2644

TTFT (ms)

28.8

Peak mem (GB)

Hardware

Chip M3 Ultra (80c)

Memory 512 GB

GPU Cores 80

Software

oMLX v0.3.9rc1

macOS macOS 26.5

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	387.3	32.6	28.8 GB	current
4k	421.2	31.2	30.3 GB	view
8k	420.6	30.7	31.3 GB	view
16k	409.9	29.5	32.8 GB	view
32k	384.5	28.0	35.8 GB	view
64k	335.1	24.2	41.8 GB	view