← Back to community benchmarks

gpt-oss-20b-MXFP4-Q8

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

Performance

1k

tokens

684.2

PP tok/s

13.1

TG tok/s

1497

TTFT (ms)

12.0

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 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	684.2	13.1	12.0 GB	current
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	view