← Back to community benchmarks

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

M5 Pro (20c) · 64 GB · 4bit · 2026-05-08

Performance

1k

tokens

423.3

PP tok/s

17.3

TG tok/s

2419

TTFT (ms)

15.8

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.3.9.dev1

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	423.3	17.3	15.8 GB	current
4k	459.4	17.1	17.3 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	17.3	1.00×
2×	31.2	1.80×
4×	40.3	2.33×