← Back to community benchmarks

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

M5 Max (40c) · 48 GB · 4bit · 2026-05-23

Performance

4k

tokens

833.0

PP tok/s

32.7

TG tok/s

4917

TTFT (ms)

17.3

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 48 GB

GPU Cores 40

Software

oMLX v0.3.9

macOS macOS 26.5

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	781.3	33.4	15.8 GB	view
4k	833.0	32.7	17.3 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	33.4	1.00×
2×	55.2	1.65×
4×	67.2	2.01×
8×	72.3	2.16×