← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M5 Pro (20c) · 64 GB · 4bit · 2026-05-18

Performance

8k

tokens

465.8

PP tok/s

24.9

TG tok/s

17586

TTFT (ms)

19.2

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.3.9.dev2

macOS macOS 26.4

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	429.2	26.5	16.7 GB	view
8k	465.8	24.9	19.2 GB	current
16k	443.3	23.4	20.7 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	26.5	1.00×
2×	31.2	1.18×
4×	41.2	1.55×