← Back to community benchmarks

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

M5 (10c) · 24 GB · 4bit · 2026-05-18

Performance

1k

tokens

220.5

PP tok/s

8.0

TG tok/s

4645

TTFT (ms)

15.8

Peak mem (GB)

Hardware

Chip M5 (10c)

Memory 24 GB

GPU Cores 10

Software

oMLX v0.3.9.dev2

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	220.5	8.0	15.8 GB	current
4k	232.4	8.0	17.2 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	8.0	1.00×
2×	16.7	2.09×
4×	22.8	2.85×