← Back to community benchmarks

Qwen3.5-27BMTP

M3 Ultra (60c) · 96 GB · 4bit · 2026-05-22

Performance

1k

tokens

304.6

PP tok/s

48.2

TG tok/s

3361

TTFT (ms)

16.1

Peak mem (GB)

Hardware

Chip M3 Ultra (60c)

Memory 96 GB

GPU Cores 60

Software

oMLX v0.3.9

macOS macOS 26.3.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	304.6	48.2	16.1 GB	current
4k	322.1	46.3	17.6 GB	view
8k	320.3	44.9	18.6 GB	view
16k	312.1	42.3	20.1 GB	view
32k	293.7	36.0	23.1 GB	view