10 actions in 8 pieces of software · ranked by words, meaning and measured trust · 662 ms
modelrecord21,084 downloads/month
- image-text-to-text
Task: image-text-to-text
- image-text-to-text
modelrecord
- text+image+video->text
Takes text, image, video; returns text.
- tool-calling
Can call tools (function calling).
- structured-outputs
Can return JSON matching a schema.
- text+image+video->text
modelrecord36,515 downloads/month
- text-generation
Task: text-generation
- text-generation
MCP serverrecord
- qwen2_5_coder_7b_gguf__lambda_
modelrecord1,098 downloads/month
- robotics
Task: robotics
- robotics
- 6Empero 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
- 7Huihui Qwen3.8 27B Abliterated GGUFdemo or tutorialno passport yet
MCP serverrecord
- Huihui_Qwen3_8_27B_abliterated_demo__lambda_
- 8Qwen3.8 27B OBLITERATED GGUFdemo or tutorialno passport yet
MCP serverrecord
- qwen38_27b_obliterated_gguf_chat
Stream a multi-turn response from Qwen3.8-27B-OBLITERATED Q4_K_M.
- qwen38_27b_obliterated_gguf_chat
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.