← Back to community benchmarks

Qwen3.6-27B-oQ6e

M5 Max (40c) · 128 GB · 6bit · 2026-05-05

Performance

1k

tokens

489.2

PP tok/s

19.3

TG tok/s

2093

TTFT (ms)

22.4

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.7

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	489.2	19.3	22.4 GB	current
4k	592.4	21.3	23.8 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	19.3	1.00×
2×	32.3	1.67×
4×	39.0	2.02×