← Back to community benchmarks

Jundot--Qwen3.6-27B-oQ8-mtp

M5 Max (40c) · 48 GB · 8bit · 2026-05-19

Performance

1k

tokens

728.3

PP tok/s

18.4

TG tok/s

1406

TTFT (ms)

28.3

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 48 GB

GPU Cores 40

Software

oMLX v0.3.9.dev2

macOS macOS 26.5

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	728.3	18.4	28.3 GB	current
4k	866.1	18.1	29.8 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	18.4	1.00×
2×	35.1	1.91×
4×	51.3	2.79×