← Back to community benchmarks

Qwen3.6-27B-mtp

M2 Max (38c) · 96 GB · 8bit · 2026-04-29

Performance

1k

tokens

117.0

PP tok/s

12.4

TG tok/s

8749

TTFT (ms)

27.6

Peak mem (GB)

Hardware

Chip M2 Max (38c)

Memory 96 GB

GPU Cores 38

Software

oMLX v0.3.8rc1

macOS macOS 26.2

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	117.0	12.4	27.6 GB	current
4k	120.3	12.2	29.0 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	12.4	1.00×
2×	19.4	1.56×
4×	20.8	1.68×