The AI tested about 20 models on my machine and found the best fit
He had the AI benchmark around 20 models on his own machine and give him a report comparing run speed and quality. After 7 hours of testing it said gpt-oss-20b was the best fit for his setup, and that is the one he chose.
How it works
- The AI runs about 20 models on his machine
- It compares run speed and quality over 7 hours of testing
- It writes a report
- He chooses gpt-oss-20b based on the result
Why it’s worth knowing
He did not read a single benchmark chart. The AI ran the tests on his own machine for 7 hours and handed him a report and a pick.
Where it’s from
Summarized from a public post on bsky.app. See the original ↗