← Back to community benchmarks

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

M5 (10c) · 24 GB · 4bit · 2026-05-18

Performance

4k

tokens

232.4

PP tok/s

8.0

TG tok/s

17625

TTFT (ms)

17.2

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 4,096

Performance by Context Length

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

Batching Results

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