← Back to community benchmarks

Qwen3.6-27B-MTPLX-Optimized

M4 Max (40c) · 64 GB · 4bit · 2026-05-06

Performance

4k

tokens

243.5

PP tok/s

23.5

TG tok/s

16825

TTFT (ms)

21.1

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.9.dev1

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	241.1	23.8	19.6 GB	view
4k	243.5	23.5	21.1 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	23.8	1.00×
2×	44.8	1.88×
4×	53.8	2.26×