← Back to community benchmarks

Qwen3.6-27B-mxfp8

M5 Max (40c) · 128 GB · 8bit · 2026-04-29

Performance

1k

tokens

715.0

PP tok/s

19.3

TG tok/s

1432

TTFT (ms)

27.6

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.8rc1

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	715.0	19.3	27.6 GB	current
4k	742.3	19.0	29.0 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	19.3	1.00×
2×	30.1	1.56×
4×	35.0	1.81×