← Back to community benchmarks

Qwen3.6-27B-UD-Q4_K_XL

M4 Max (32c) · 36 GB · 4bit · 2026-05-04

Performance

16k

tokens

765.3

PP tok/s

8.9

TG tok/s

21409

TTFT (ms)

25.4

Peak mem (GB)

Hardware

Chip M4 Max (32c)

Memory 36 GB

GPU Cores 32

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	195.7	16.5	21.7 GB	view
4k	201.1	16.4	23.2 GB	view
8k	199.4	16.1	24.2 GB	view
16k	765.3	8.9	25.4 GB	current
32k	751.7	8.8	26.8 GB	view