← Back to community benchmarks

Qwen3.6-27B-oQ8-mtp

M1 Max (24c) · 64 GB · 8bit · 2026-05-09

Performance

1k

tokens

67.5

PP tok/s

13.5

TG tok/s

15178

TTFT (ms)

28.8

Peak mem (GB)

Hardware

Chip M1 Max (24c)

Memory 64 GB

GPU Cores 24

Software

oMLX v0.3.9.dev1

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	67.5	13.5	28.8 GB	current
4k	68.6	14.1	30.3 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	13.5	1.00×
2×	29.4	2.18×