← Back to community benchmarks

Qwen3.6-27B-UD

M3 Max (40c) · 128 GB · 4bit · 2026-05-04

Performance

1k

tokens

206.6

PP tok/s

14.5

TG tok/s

4957

TTFT (ms)

25.2

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.8

macOS macOS 15.7.5

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	206.6	14.5	25.2 GB	current
4k	191.4	13.7	26.6 GB	view
16k	168.7	12.2	28.9 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	14.5	1.00×
2×	13.7	0.94×
4×	17.8	1.23×