10 actions in 8 pieces of software · ranked by words, meaning and measured trust · 592 ms
modelrecord13,654 downloads/month
- image-text-to-text
Task: image-text-to-text
- image-text-to-text
modelrecord233,766 downloads/month
- text-generation
Task: text-generation
- text-generation
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
modelrecord27,573 downloads/month
- translation
Task: translation
- translation
modelrecord
- text->text
Takes text; returns text.
- text->text
modelrecord
- google/gemini-3-flash
Google's most intelligent model built for speed with frontier intelligence, superior search, and grounding
- google/gemini-3-flash
modelrecord391 downloads/month
- robotics
Task: robotics
- robotics
- 8Qwen2.5-VL 32B GGUF Chatdemo or tutorialno passport yet
MCP serverrecord
- qwen2_5_vl_32b_gguf_load_model
Load (or switch to) a GGUF quantization of Qwen2.5-VL-32B.
- qwen2_5_vl_32b_gguf_load_model
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.