← Back to community benchmarks

Qwen3.6-27BoQ4

M5 Pro (20c) · 48 GB · 4bit · 2026-06-04

Performance

1k

tokens

415.5

PP tok/s

17.1

TG tok/s

2464

TTFT (ms)

16.3

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 48 GB

GPU Cores 20

Software

oMLX v0.4.0

macOS macOS 26.5.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	415.5	17.1	16.3 GB	current
4k	439.1	16.7	17.6 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	17.1	1.00×
2×	32.3	1.89×
4×	43.5	2.54×