← Back to community benchmarks

Qwen3.6-27B-oQ8-fp16-mtp

M1 Ultra (64c) · 128 GB · 8bit · 2026-05-10

Performance

8k

tokens

276.5

PP tok/s

26.1

TG tok/s

29632

TTFT (ms)

31.3

Peak mem (GB)

Hardware

Chip M1 Ultra (64c)

Memory 128 GB

GPU Cores 64

Software

oMLX v0.3.9.dev1

macOS macOS 26.5

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	252.3	23.7	28.8 GB	view
4k	274.5	26.3	30.3 GB	view
8k	276.5	26.1	31.3 GB	current