← Back to community benchmarks

gpt-oss-20b-MXFP4-Q8

M4 Pro (16c) · 48 GB · 4bit · 2026-05-02

Performance

8k

tokens

609.4

PP tok/s

56.3

TG tok/s

13443

TTFT (ms)

12.0

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 48 GB

GPU Cores 16

Software

oMLX v0.3.8

macOS macOS 15.5

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	502.8	63.5	11.8 GB	view
4k	599.5	61.1	11.8 GB	view
8k	609.4	56.3	12.0 GB	current