← Back to community benchmarks

Qwen3.6-27B-MTPLX-Optimized-Quality

M5 Max (40c) · 64 GB · 4bit · 2026-05-18

Performance

1k

tokens

723.8

PP tok/s

18.1

TG tok/s

1415

TTFT (ms)

28.3

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 64 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	723.8	18.1	28.3 GB	current
4k	861.0	17.9	29.8 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	18.1	1.00×
2×	35.2	1.94×
4×	49.5	2.73×