← Back to community benchmarks

Qwen3.6-27B-OptiQ

M4 Max (40c) · 48 GB · 4bit · 2026-04-26

Performance

4k

tokens

250.7

PP tok/s

25.8

TG tok/s

16340

TTFT (ms)

18.5

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 48 GB

GPU Cores 40

Software

oMLX v0.3.7rc1

macOS macOS 26.2

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	242.8	26.7	17.1 GB	view
4k	250.7	25.8	18.5 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	26.7	1.00×
2×	50.1	1.88×
4×	59.5	2.23×