News for hackers. Stuff that matters.

A comment on Gemma 3 270M: The compact model for hyper-efficient AI. Parent comment

Re:Gemma 3 270M: The compact model for hyper-efficient AI by riedel on Thursday August 14, 2025 @06:40PM (#44906552)
Would be great to have it included in the Google Edge AI gallery android app.
[ Parent | on HN ]
Re:Gemma 3 270M: The compact model for hyper-efficient AI by rshemet on Thursday August 14, 2025 @08:38PM (#44907399)
you can run it in Cactus Chat (download from the Play Store)
[ Parent | on HN ]
Re:Gemma 3 270M: The compact model for hyper-efficient AI by nh43215rgb on Thursday August 14, 2025 @11:31PM (#44908343)
what model do you input in Cactus Chat? Seems like it's not one of the preset models and ggml-org/gemma-3-270m-GGUF on hf says Note This is a base (pre-trained) model. Do not use for chat!. Is there an alternative model that you can share so that I can put into cactus chat app?
[ Parent | on HN ]
Re:Gemma 3 270M: The compact model for hyper-efficient AI by bbcc90 on Friday August 15, 2025 @01:24AM (#44908882)
it does work; just download from HF and load in the app
[ Parent | on HN ]