10 actions in 8 pieces of software · ranked by words, meaning and measured trust · 605 ms

1. 1MT2-Gen2_gemma-3-12Bverified and signedpassport

   modelrecord16 downloads/month

   • image-text-to-text

     Task: image-text-to-text

2. 2google-deepmind/gemma-3-12b-itverified and signedpassport

   modelrecord

   • google-deepmind/gemma-3-12b-it

     Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models.

3. 3amoral-gemma3-12B-v2verified and signedpassport

   modelrecord41 downloads/month

   • text-generation

     Task: text-generation

4. 4gemma-4-12Bverified and signedpassport

   modelrecord75,733 downloads/month

   • any-to-any

     Task: any-to-any

5. 5Google: Gemma 3 12Bverified and signedpassport

   modelrecord

   • tool-calling

     Can call tools (function calling).

   • text+image->text

     Takes text, image; returns text.

   • structured-outputs

     Can return JSON matching a schema.

6. 6google-deepmind/gemma-3-27b-itverified and signedpassport

   modelrecord

   • google-deepmind/gemma-3-27b-it

     Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models.

7. 7google-deepmind/gemma-3-4b-itverified and signedpassport

   modelrecord

   • google-deepmind/gemma-3-4b-it

     Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models.

8. 8lucataco/gemma-4-31b-itverified and signedpassport

   modelrecord

   • lucataco/gemma-4-31b-it

     Gemma 4 31B Instruct - Google open-weight VLM (image + text in, text out)