FunctionGemma 270M Model

#1

Post by mariobm » Thu, Dec 18, 2025, 6:26 PM UTC

Re: FunctionGemma 270M Model

#2

Post by canyon289 » Thu, Dec 18, 2025, 6:41 PM UTC

Hi all, I'm a research lead on this model. Same as every model release post, I enjoy working at Google for a multitude of reasons, and opinions here are my own.

Happy to answer whatever technical questions I can!

Re: FunctionGemma 270M Model

#3

Post by xnx » Thu, Dec 18, 2025, 7:16 PM UTC

canyon289 wrote: post #2

Hi all, I'm a research lead on this model. Same as every model release post, I enjoy working at Google for a multitude of reasons, and opinions here are my own. Happy to answer whatever technical questions I can!

Cool game! Amazing it can run in the browser. My mind was blown when I saw you could give goal based commands vs prescriptive ones. https://huggingface.co/spaces/webml-community/FunctionGemma-...

Re: FunctionGemma 270M Model

#4

Post by carlcortright » Thu, Dec 18, 2025, 7:25 PM UTC

canyon289 wrote: post #2

Hi all, I'm a research lead on this model. Same as every model release post, I enjoy working at Google for a multitude of reasons, and opinions here are my own. Happy to answer whatever technical questions I can!

Very cool model! Congrats on the work!

Re: FunctionGemma 270M Model

#5

Post by nateb2022 » Thu, Dec 18, 2025, 7:28 PM UTC

Ollama link too: https://ollama.com/library/functiongemma

Re: FunctionGemma 270M Model

#6

Post by NitpickLawyer » Thu, Dec 18, 2025, 7:32 PM UTC

canyon289 wrote: post #2

Hi all, I'm a research lead on this model. Same as every model release post, I enjoy working at Google for a multitude of reasons, and opinions here are my own. Happy to answer whatever technical questions I can!

Wen gemma4? :)

But on a serious note, I'm happy to see more research going into vSLMs (very small...) My "dream" scenario is to have the "agentic" stuff run locally, and call into the "big guns" as needed. Being able to finetune these small models on consumer cards is awesome, and can open up a lot of niche stuff for local / private use.

Re: FunctionGemma 270M Model

#7

Post by canyon289 » Thu, Dec 18, 2025, 7:38 PM UTC

NitpickLawyer wrote: post #6

canyon289 wrote: post #2

Hi all, I'm a research lead on this model. Same as every model release post, I enjoy working at Google for a multitude of reasons, and opinions here are my own. Happy to answer whatever technical questions I can!

Wen gemma4? :) But on a serious note, I'm happy to see more research going into vSLMs (very small...) My "dream" scenario is to have the "agentic" stuff run locally, and call into the "big guns" as needed. Being able to finetune these small models on consumer cards is awesome, and can open up a lot of niche stuff for local / private use.

Trust me as a daily at home Gemma user myself, I'm just excited for what's upcoming as you are, maybe even more because I have some hints for what's to come.

>My "dream" scenario is to have the "agentic" stuff run locally, and call into the "big guns" as needed.

FunctionGemma 270m is your starter pack for this, train your own functions to call out to whatever larger models you choose. It's been quite effective my testing, and the finetuning guides should show you how to add in your own capabilities.

Speaking from the research side its incredible how so many small models, not just Gemma, are achieving performance levels of must larger models from just a year or two ago. It's personally why I stay in this space.

Re: FunctionGemma 270M Model

#8

Post by canyon289 » Thu, Dec 18, 2025, 7:41 PM UTC

xnx wrote: post #3

canyon289 wrote: post #2

Hi all, I'm a research lead on this model. Same as every model release post, I enjoy working at Google for a multitude of reasons, and opinions here are my own. Happy to answer whatever technical questions I can!

Cool game! Amazing it can run in the browser. My mind was blown when I saw you could give goal based commands vs prescriptive ones. https://huggingface.co/spaces/webml-community/FunctionGemma-...

So I didn't even know this was going to be made until recently, and when I saw it, it also blew my mind. I didn't realize how far along web ml community had pushed things, and was impressed by the creativity of the HF folks with visuals and "game flow".

Personally speaking its really neat to see other people who take these models and run with them, creating things I could haven't have imagined. I'm hoping many others in the open community do the same in the coming weeks and the new year

Re: FunctionGemma 270M Model

#9

Post by canyon289 » Thu, Dec 18, 2025, 7:41 PM UTC

carlcortright wrote: post #4

canyon289 wrote: post #2

Hi all, I'm a research lead on this model. Same as every model release post, I enjoy working at Google for a multitude of reasons, and opinions here are my own. Happy to answer whatever technical questions I can!

Very cool model! Congrats on the work!

Thank you much for the kind words

Re: FunctionGemma 270M Model

#10

Post by xnx » Thu, Dec 18, 2025, 7:41 PM UTC

canyon289 wrote: post #2

Hi all, I'm a research lead on this model. Same as every model release post, I enjoy working at Google for a multitude of reasons, and opinions here are my own. Happy to answer whatever technical questions I can!

Not FunctionGemma related, but would love to see an open weights model from Google for speech to text transcription (diarization, timestamps, etc.).

Whisper is old and resource intensive for the accuracy it provides.