9 actions in 9 pieces of software · ranked by words, meaning and measured trust · 627 ms
modelrecord309,153 downloads/month
- any-to-any
Task: any-to-any
- any-to-any
modelrecord11,137 downloads/month
- image-text-to-text
Task: image-text-to-text
- image-text-to-text
modelrecord
- lucataco/gemma-4-31b-it
Gemma 4 31B Instruct - Google open-weight VLM (image + text in, text out)
- lucataco/gemma-4-31b-it
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
modelrecord18,277 downloads/month
- text-generation
Task: text-generation
- text-generation
modelrecord
- google-deepmind/gemma-2b-it
2B instruct version of Google’s Gemma model
- google-deepmind/gemma-2b-it
- 7Gemma 3 12B IT Heretic Demodemo or tutorialno passport yet
MCP serverrecord
- gemma_3_12b_it_heretic_demo__lambda_
- 8Gemma 4 E2B · Legal-versedemo or tutorialno passport yet
MCP serverrecord
- gemma_4_e2b_mlx_demo_chat
Chat with the exact Legal-verse Gemma 4 E2B MLX checkpoint.
- gemma_4_e2b_mlx_demo_chat
- 9Gemma 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).
- gemma4_31b_chat_respond
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.