← Back to community benchmarks

Qwen3.6-27B-oQ8-mtp

M5 Max (40c) · 64 GB · 8bit · 2026-05-16

Performance

1k

tokens

720.6

PP tok/s

27.4

TG tok/s

1421

TTFT (ms)

28.8

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.9.dev2

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	720.6	27.4	28.8 GB	current
4k	698.0	29.6	30.3 GB	view
8k	664.3	27.9	31.3 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	27.4	1.00×
2×	33.2	1.21×
4×	44.5	1.62×