← Back to community benchmarks

gpt-oss-20b-MXFP4-Q8

M4 (10c) · 32 GB · 4bit · 2026-04-20

Performance

1k

tokens

379.4

PP tok/s

34.9

TG tok/s

2699

TTFT (ms)

11.7

Peak mem (GB)

Hardware

Chip M4 (10c)

Memory 32 GB

GPU Cores 10

Software

oMLX v0.3.6

macOS macOS 26.4

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	379.4	34.9	11.7 GB	current
4k	402.9	32.4	11.8 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	34.9	1.00×
2×	47.2	1.35×
4×	54.9	1.57×