Estimated Thinking/Reasoning Token Usages For Each Modes

#65
by asif00 - opened

Is there a estimated or hard token counts or limits for each of the reasoning modes [Low, Medium, High] for 120B and 20B?

Thanks in advanced!

not that I know of, but it does use much less than most other models. You can try at gpt-oss.com and see how many tokens it's using

Sign up or log in to comment