← Back to community benchmarks

Qwen3.6-27B-oQ6-mtp

M1 Ultra (64c) · 128 GB · 6bit · 2026-05-19

Performance

16k

tokens

161.8

PP tok/s

19.7

TG tok/s

101254

TTFT (ms)

26.6

Peak mem (GB)

Hardware

Chip M1 Ultra (64c)

Memory 128 GB

GPU Cores 64

Software

oMLX v0.3.9rc1

macOS macOS 26.5

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	155.4	22.2	22.6 GB	view
8k	164.3	20.7	25.1 GB	view
16k	161.8	19.7	26.6 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	22.2	1.00×
2×	27.8	1.25×
4×	31.9	1.44×