← Back to community benchmarks

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

M5 Pro (16c) · 48 GB · 4bit · 2026-05-15

Performance

4k

tokens

389.7

PP tok/s

17.6

TG tok/s

10510

TTFT (ms)

17.3

Peak mem (GB)

Hardware

Chip M5 Pro (16c)

Memory 48 GB

GPU Cores 16

Software

oMLX v0.3.9.dev2

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	354.8	18.0	15.8 GB	view
4k	389.7	17.6	17.3 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	18.0	1.00×
2×	29.7	1.65×
4×	36.2	2.01×