← Back to community benchmarks

gpt-oss-20b-reap-0.4-mxfp4

M3 Max (40c) · 128 GB · 4bit · 2026-04-28

Performance

1k

tokens

1,069

PP tok/s

87.2

TG tok/s

958

TTFT (ms)

8.2

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.7rc2

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,069	87.2	8.2 GB	current
4k	1,253	81.7	8.3 GB	view
16k	1,046	57.5	8.5 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	87.2	1.00×
2×	103.0	1.18×
4×	151.3	1.74×