← Back to community benchmarks

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

M2 Ultra (76c) · 192 GB · 8bit · 2026-05-17

Performance

1k

tokens

355.4

PP tok/s

29.8

TG tok/s

2881

TTFT (ms)

28.8

Peak mem (GB)

Hardware

Chip M2 Ultra (76c)

Memory 192 GB

GPU Cores 76

Software

oMLX v0.3.9.dev1

macOS macOS 26.4

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	355.4	29.8	28.8 GB	current
4k	393.3	30.7	30.3 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	29.8	1.00×
2×	38.5	1.29×
4×	39.2	1.32×