← Back to community benchmarks

Qwen3.6-27B-oQ8-mtp

M2 Ultra (76c) · 128 GB · 8bit · 2026-05-07

Performance

8k

tokens

226.6

PP tok/s

28.2

TG tok/s

36145

TTFT (ms)

31.3

Peak mem (GB)

Hardware

Chip M2 Ultra (76c)

Memory 128 GB

GPU Cores 76

Software

oMLX v0.3.9.dev1

macOS macOS 15.7.5

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	210.1	30.8	28.8 GB	view
4k	226.1	29.3	30.3 GB	view
8k	226.6	28.2	31.3 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	30.8	1.00×
2×	37.9	1.23×
4×	51.8	1.68×