9 actions in 7 pieces of software · ranked by words, meaning and measured trust · 596 ms
modelrecord22,713 downloads/month
- image-text-to-text
Task: image-text-to-text
- image-text-to-text
modelrecord1,085,603 downloads/month
- text-generation
Task: text-generation
- text-generation
modelrecord77,100 downloads/month
- any-to-any
Task: any-to-any
- any-to-any
modelrecord
- tool-calling
Can call tools (function calling).
- text+image->text
Takes text, image; returns text.
- structured-outputs
Can return JSON matching a schema.
- tool-calling
- 5Muse Glimmer 30B Demodemo or tutorialno passport yet
MCP serverrecord
- Muse_Glimmer_30B_Demo_chat
Stream a Muse Glimmer 30B reply for text, image, or video chat. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool
- Muse_Glimmer_30B_Demo_chat
- 6Qwen3.8 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
- 7Gemma 3 4B VL Heretic Thinking GGUFdemo or tutorialno passport yet
MCP serverrecord
- Gemma_3_4B_VL_Heretic_Thinking_chat_ask
Send one message, optionally with an image, to Gemma-3-4B-VL Gemini-Pro Heretic Thinking and return its answer. Returns: The model's final answer as plain text.
- Gemma_3_4B_VL_Heretic_Thinking_chat_ask
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.