← Back to community benchmarks

Qwen3.6-27B-UD

M5 Pro (16c) · 48 GB · 4bit · 2026-06-04

Performance

1k

tokens

339.2

PP tok/s

11.2

TG tok/s

3019

TTFT (ms)

24.8

Peak mem (GB)

Hardware

Chip M5 Pro (16c)

Memory 48 GB

GPU Cores 16

Software

oMLX v0.4.0rc1

macOS macOS 26.5.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	339.2	11.2	24.8 GB	current
4k	361.8	11.0	26.1 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	11.2	1.00×
2×	12.5	1.12×
4×	20.2	1.80×