← Back to community benchmarks

Qwen3.6-27B-oQ4-fp16-mtp

M2 Max (30c) · 32 GB · 4bit · 2026-06-03

Performance

1k

tokens

141.6

PP tok/s

17.9

TG tok/s

7234

TTFT (ms)

16.5

Peak mem (GB)

Hardware

Chip M2 Max (30c)

Memory 32 GB

GPU Cores 30

Software

oMLX v0.4.0

macOS macOS 14.6

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	141.6	17.9	16.5 GB	current
4k	151.1	20.8	17.7 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	17.9	1.00×
2×	25.9	1.45×