10 actions in 10 pieces of software · ranked by words, meaning and measured trust · 589 ms

1. 1Gemma-4-Novelist-Eclipse-31Bverified and signedpassport

   modelrecord672 downloads/month

   • text-generation

     Task: text-generation

2. 2lucataco/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)

3. 3gemma-4-31B-it-AWQ-4bitverified and signedpassport

   modelrecord67,280 downloads/month

   • image-text-to-text

     Task: image-text-to-text

4. 4Huihui-gemma-4-31B-it-qat-q4_0-unquantized-abliterated-GGUFverified and signedpassport

   modelrecord28,148 downloads/month

   • any-to-any

     Task: any-to-any

5. 5Google: Gemma 4 31B (free)verified and signedpassport

   modelrecord

   • tool-calling

     Can call tools (function calling).

6. 6Google: Gemma 4 31Bverified and signedpassport

   modelrecord

   • structured-outputs

     Can return JSON matching a schema.

7. 7prunaai/gemma-4-26b-a4b-fastverified and signedpassport

   modelrecord

   • prunaai/gemma-4-26b-a4b-fast

     This is a version of the MoE Gemma 4 26B optimised by Pruna AI.

8. 8google-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.

9. 9google-deepmind/gemma-2b-itverified and signedpassport

   modelrecord

   • google-deepmind/gemma-2b-it

     2B instruct version of Google’s Gemma model

10. 10Gemma 4 31B — Chatdemo or tutorialno passport yet

    MCP serverrecord

    • gemma4_31b_chat_respond

      Reply to a single chat turn using Gemma 4 31B (4-bit).