← Back to community benchmarks

Qwen3.6-27B-UD

M5 Pro (20c) · 64 GB · 4bit · 2026-06-14

Performance

1k

tokens

382.1

PP tok/s

11.5

TG tok/s

2680

TTFT (ms)

25.1

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.4.4rc1

macOS macOS 26.5.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	382.1	11.5	25.1 GB	current
4k	426.9	11.3	26.1 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	11.5	1.00×
2×	14.6	1.27×
4×	24.7	2.15×