← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M5 Pro (20c) · 48 GB · 4bit · 2026-05-14

Performance

1k

tokens

428.2

PP tok/s

25.8

TG tok/s

2391

TTFT (ms)

16.7

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 48 GB

GPU Cores 20

Software

oMLX v0.3.9.dev2

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	428.2	25.8	16.7 GB	current
4k	468.2	25.8	18.2 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	25.8	1.00×
2×	31.2	1.21×
4×	40.0	1.55×