← Back to community benchmarks

Qwen3.6-27B-UD

M3 Ultra (60c) · 96 GB · 4bit · 2026-04-26

Performance

1k

tokens

282.0

PP tok/s

26.1

TG tok/s

3631

TTFT (ms)

24.7

Peak mem (GB)

Hardware

Chip M3 Ultra (60c)

Memory 96 GB

GPU Cores 60

Software

oMLX v0.3.6

macOS macOS 15.6

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	282.0	26.1	24.7 GB	current
4k	311.2	25.2	26.1 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	26.1	1.00×
2×	27.0	1.03×
4×	43.0	1.65×