← Back to community benchmarks

Qwen3.6-27B

M5 Pro (20c) · 64 GB · 4bit · 2026-06-22

Performance

4k

tokens

462.1

PP tok/s

17.5

TG tok/s

8864

TTFT (ms)

17.3

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.4.4

macOS macOS 27.0

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	424.1	17.9	15.8 GB	view
4k	462.1	17.5	17.3 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	17.9	1.00×
2×	31.8	1.78×
4×	43.4	2.42×