← Back to community benchmarks

Qwen3.6-27B-MXFP4-MTP

M3 Max (30c) · 36 GB · 4bit · 2026-05-21

Performance

1k

tokens

151.5

PP tok/s

14.4

TG tok/s

6759

TTFT (ms)

15.9

Peak mem (GB)

Hardware

Chip M3 Max (30c)

Memory 36 GB

GPU Cores 30

Software

oMLX v0.3.9rc1

macOS macOS 26.5

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	151.5	14.4	15.9 GB	current
4k	161.6	14.1	17.3 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	14.4	1.00×
2×	34.6	2.40×
4×	42.6	2.96×