← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M4 Pro (20c) · 64 GB · 4bit · 2026-05-07

Performance

8k

tokens

106.5

PP tok/s

19.8

TG tok/s

76938

TTFT (ms)

19.2

Peak mem (GB)

Hardware

Chip M4 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.3.9.dev1

macOS macOS 26.3.1

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	121.0	21.6	16.8 GB	view
4k	111.0	20.0	18.2 GB	view
8k	106.5	19.8	19.2 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	21.6	1.00×
2×	24.4	1.13×
4×	26.6	1.23×