← Back to community benchmarks

Qwen3.6-27B-oQ8-mtp

M5 Max (40c) · 128 GB · 8bit · 2026-05-19

Performance

8k

tokens

791.5

PP tok/s

28.5

TG tok/s

10350

TTFT (ms)

31.7

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.9.dev2

macOS macOS 26.5

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	718.1	26.2	29.3 GB	view
4k	804.2	28.9	30.7 GB	view
8k	791.5	28.5	31.7 GB	current
16k	756.9	26.7	33.2 GB	view
32k	695.0	25.6	36.2 GB	view