← Back to community benchmarks

gpt-oss-20b-MXFP4-Q8

M5 Pro (20c) · 64 GB · 4bit · 2026-03-23

Performance

4k

tokens

2,177

PP tok/s

75.0

TG tok/s

1882

TTFT (ms)

11.8

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.2.19

macOS macOS 26.3.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,898	80.6	11.7 GB	view
4k	2,177	75.0	11.8 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	80.6	1.00×
2×	114.1	1.42×
4×	134.1	1.66×