← Back to community benchmarks

Qwen3.6-27B-oQ8-mtp

M5 Max (40c) · 64 GB · 8bit · 2026-05-11

Performance

16k

tokens

781.0

PP tok/s

27.2

TG tok/s

20978

TTFT (ms)

32.5

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.9.dev1

macOS macOS 26.4.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	730.6	30.6	28.8 GB	view
4k	861.2	30.7	30.3 GB	view
16k	781.0	27.2	32.5 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	30.6	1.00×
2×	35.3	1.15×
4×	45.9	1.50×