← Back to community benchmarks

gpt-oss-20b-MXFP4-Q8

M4 Pro (16c) · 24 GB · 4bit · 2026-06-05

Performance

4k

tokens

637.7

PP tok/s

59.9

TG tok/s

6423

TTFT (ms)

11.8

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 24 GB

GPU Cores 16

Software

oMLX v0.4.2.dev2

macOS macOS 26.5

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	545.8	64.2	11.8 GB	view
4k	637.7	59.9	11.8 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	64.2	1.00×
2×	87.5	1.36×
4×	98.7	1.54×