← Back to community benchmarks

gpt-oss-20b-MXFP4-Q8

M4 (10c) · 32 GB · 4bit · 2026-04-18

Performance

8k

tokens

391.7

PP tok/s

29.8

TG tok/s

20913

TTFT (ms)

11.9

Peak mem (GB)

Hardware

Chip M4 (10c)

Memory 32 GB

GPU Cores 10

Software

oMLX v0.3.6

macOS macOS 26.3.1

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	377.5	35.5	11.7 GB	view
4k	402.8	33.1	11.8 GB	view
8k	391.7	29.8	11.9 GB	current