← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M2 Ultra (60c) · 128 GB · 4bit · 2026-05-11

Performance

8k

tokens

178.5

PP tok/s

29.0

TG tok/s

45893

TTFT (ms)

19.2

Peak mem (GB)

Hardware

Chip M2 Ultra (60c)

Memory 128 GB

GPU Cores 60

Software

oMLX v0.3.9.dev1

macOS macOS 15.6.1

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	171.8	32.1	16.8 GB	view
4k	179.0	30.5	18.2 GB	view
8k	178.5	29.0	19.2 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	32.1	1.00×
2×	38.9	1.21×
4×	43.3	1.35×