is anyone using GPT-OSS 120B ? And Why i feel its useless
1 Like
It’s particularly useful if you’re trying to test agentic flows you plan to deploy (not for writing code) on a GPT-OSS-120B or other models in the same class as o4-mini, Gemma, Flash or Haiku.
These models aren’t as capable, but use about 100x less compute than Opus.