GPT-OSS-20B

Model mdl-3k8m1q

Back to Models
TU

GPT-OSS-20B

Ready

Compact open-weight model tuned for fast inference and on-device deployment

LanguageCode
Created

Mar 11, 2026

Parameters

20B

Accuracy

90.4%

Training Time

5h 50m

Data Sources

Image Dataset Alpha

gs://trinidy-media/images-alpha

890.0K records

Internal NAS Archive

nas://192.168.1.40/ml-archive

340.0K records

Deploy this model to get an inference endpoint