← Back to community benchmarks

gpt-oss-20b-MXFP4-Q8

M2 (10c) · 24 GB · 4bit · 2026-03-12

Performance

1k

tokens

129.6

PP tok/s

27.3

TG tok/s

7901

TTFT (ms)

11.4

Peak mem (GB)

Hardware

Chip M2 (10c)

Memory 24 GB

GPU Cores 10

Software

oMLX v0.2.10

macOS macOS 26.3.1

Context 1,024

Batching Results

Batch Size	TG tok/s	Speedup
1×	27.3	1.00×
2×	35.5	1.30×