10 actions in 10 pieces of software · ranked by words, meaning and measured trust · 576 ms
modelrecord339 downloads/month
- text-generation
Task: text-generation
- text-generation
modelrecord45 downloads/month
- image-text-to-text
Task: image-text-to-text
- image-text-to-text
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.
- google-deepmind/gemma-3-12b-it
modelrecord77,100 downloads/month
- any-to-any
Task: any-to-any
- any-to-any
modelrecord
- google-deepmind/gemma-2b-it
2B instruct version of Google’s Gemma model
- google-deepmind/gemma-2b-it
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.
- google-deepmind/gemma-3-27b-it
- 7Gemma 3 12B IT Heretic Demodemo or tutorialno passport yet
MCP serverrecord
- gemma_3_12b_it_heretic_demo__lambda_
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.
- google-deepmind/gemma-3-4b-it
modelrecord
- google-deepmind/gemma-2-2b-it
Gemma2 2b Instruction-tuned variant by Google
- google-deepmind/gemma-2-2b-it
modelrecord
- google-deepmind/gemma-7b-it
7B instruct version of Google’s Gemma model
- google-deepmind/gemma-7b-it
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.