← Back to community benchmarks

gpt-oss-20b-MXFP4-Q8

M4 Pro (20c) · 64 GB · 4bit · 2026-04-15

Performance

16k

tokens

712.5

PP tok/s

51.1

TG tok/s

22995

TTFT (ms)

12.1

Peak mem (GB)

Hardware

Chip M4 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.3.5

macOS macOS 26.3.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	684.2	13.1	12.0 GB	view
4k	579.3	58.5	11.8 GB	view
8k	774.3	58.7	11.9 GB	view
16k	712.5	51.1	12.1 GB	current