10 actions in 9 pieces of software · ranked by words, meaning and measured trust · 661 ms
modelrecord410 downloads/month
- robotics
Task: robotics
- robotics
modelrecord1,242,465 downloads/month
- image-text-to-text
Task: image-text-to-text
- image-text-to-text
modelrecord46,371 downloads/month
- text-generation
Task: text-generation
- text-generation
modelrecord11,504 downloads/month
- text-ranking
Task: text-ranking
- text-ranking
libraryggml-org/llama.cpprecord5,488,885 downloads/month
- gguf
modelrecord13,222 downloads/month
- any-to-any
Task: any-to-any
- any-to-any
- 7Empero 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
- 8Qwen2.5-VL 32B GGUF Chatdemo or tutorialno passport yet
MCP serverrecord
- qwen2_5_vl_32b_gguf_refresh_status
- qwen2_5_vl_32b_gguf_load_model
Load (or switch to) a GGUF quantization of Qwen2.5-VL-32B.
- 9Qwen3.8 27B Uncensored GGUFdemo or tutorialno passport yet
MCP serverrecord
- qwen38_27b_uncensored_gguf_chat
Stream a multi-turn response from the official Qwen3.8 Q4_K_M GGUF.
- qwen38_27b_uncensored_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.