← Back to community benchmarks

Qwen3.6-27B

M5 Pro (20c) · 64 GB · 8bit · 2026-06-17

Performance

1k

tokens

338.0

PP tok/s

8.6

TG tok/s

3029

TTFT (ms)

33.0

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.4.4rc2

macOS macOS 26.5.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	338.0	8.6	33.0 GB	current
4k	426.3	8.6	34.6 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	8.6	1.00×
2×	12.2	1.42×
4×	20.6	2.40×