9 actions in 8 pieces of software · ranked by words, meaning and measured trust · 508 ms
modelrecord19 downloads/month
- text-generation
Task: text-generation
- text-generation
modelrecord1,720,553 downloads/month
- feature-extraction
Task: feature-extraction
- feature-extraction
modelrecord2,412,394 downloads/month
- text-ranking
Task: text-ranking
- text-ranking
modelrecord1,089 downloads/month
- robotics
Task: robotics
- robotics
- 5Qwen3-4B Dijkstra Unlearn & Reinventdemo or tutorialno passport yet
MCP serverrecord
- qwen3_4b_thinking_2507_dijkstra_unlearn__preview
- qwen3_4b_thinking_2507_dijkstra_unlearn__lambda_
modelrecord45,669 downloads/month
- any-to-any
Task: any-to-any
- any-to-any
- 7Qwen3-4B Heretic Chatdemo or tutorialno passport yet
MCP serverrecord
- qwen3_4b_heretic_chat_respond
Chat with Qwen3-4B-Instruct-2507-heretic. Streams the model's reply token-by-token into the chat window.
- qwen3_4b_heretic_chat_respond
- 8Empero Qwen3.5-4B Hereticdemo or tutorialno passport yet
MCP serverrecord
- empero_qwen35_4b_heretic_respond
Stream a chat reply from the Empero Qwen3.5-4B Heretic Q4_K_M GGUF.
- empero_qwen35_4b_heretic_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.