← Back to community benchmarks

Qwen3.6-27B

M3 Ultra (80c) · 512 GB · 4bit · 2026-05-01

Performance

8k

tokens

424.2

PP tok/s

33.6

TG tok/s

19310

TTFT (ms)

60.2

Peak mem (GB)

Hardware

Chip M3 Ultra (80c)

Memory 512 GB

GPU Cores 80

Software

oMLX v0.3.6

macOS macOS 26.3.1

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	396.2	36.3	58.1 GB	view
4k	425.1	34.9	59.5 GB	view
8k	424.2	33.6	60.2 GB	current
16k	413.0	30.9	61.4 GB	view
32k	387.7	26.5	63.9 GB	view