← Back to community benchmarks

gpt-oss-20b-MXFP4-Q8

M4 Max (40c) · 48 GB · 4bit · 2026-05-12

Performance

4k

tokens

1,446

PP tok/s

102.7

TG tok/s

2833

TTFT (ms)

11.8

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 48 GB

GPU Cores 40

Software

oMLX v0.3.9.dev1

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	977.7	110.7	11.8 GB	view
4k	1,446	102.7	11.8 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	110.7	1.00×
2×	152.9	1.38×
4×	193.9	1.75×