← Back to community benchmarks

Qwen3.6-27B-oQ8-mtp

M4 Pro (20c) · 48 GB · 8bit · 2026-05-08

Performance

1k

tokens

121.9

PP tok/s

14.3

TG tok/s

8398

TTFT (ms)

28.8

Peak mem (GB)

Hardware

Chip M4 Pro (20c)

Memory 48 GB

GPU Cores 20

Software

oMLX v0.3.9.dev1

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	121.9	14.3	28.8 GB	current
4k	122.2	13.5	30.3 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	14.3	1.00×
2×	16.9	1.18×
4×	56.1	3.92×