← Back to community benchmarks

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

M5 (10c) · 32 GB · 4bit · 2026-06-19

Performance

1k

tokens

198.7

PP tok/s

8.6

TG tok/s

5153

TTFT (ms)

15.8

Peak mem (GB)

Hardware

Chip M5 (10c)

Memory 32 GB

GPU Cores 10

Software

oMLX v0.4.4

macOS macOS 27.0

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	198.7	8.6	15.8 GB	current
4k	204.8	8.3	17.2 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	8.6	1.00×
2×	16.5	1.92×
4×	17.4	2.02×