← Back to community benchmarks

gpt-oss-20b-MXFP4-Q8

M4 Pro (16c) · 64 GB · 4bit · 2026-03-10

Performance

1k

tokens

419.7

PP tok/s

64.5

TG tok/s

2440

TTFT (ms)

11.4

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 64 GB

GPU Cores 16

Software

oMLX v0.2.6

macOS macOS 15.6.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	419.7	64.5	11.4 GB	current
4k	479.6	57.1	11.5 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	64.5	1.00×
2×	85.3	1.32×
4×	60.0	0.93×