← Back to community benchmarks

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

M5 Max (40c) · 128 GB · 4bit · 2026-05-10

Performance

32k

tokens

1,606

PP tok/s

24.1

TG tok/s

20405

TTFT (ms)

39.0

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	791.3	33.0	34.0 GB	view
32k	1,606	24.1	39.0 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	33.0	1.00×
2×	60.3	1.83×