10 actions in 10 pieces of software · ranked by words, meaning and measured trust · 1104 ms
modelrecord1,089 downloads/month
- robotics
Task: robotics
- robotics
modelrecord3,468,517 downloads/month
- image-text-to-text
Task: image-text-to-text
- image-text-to-text
modelrecord
- tool-calling
Can call tools (function calling).
- tool-calling
modelrecord25,315 downloads/month
- image-to-text
Task: image-to-text
- image-to-text
modelrecord
- lucataco/qwen3-vl-8b-instruct
A powerful vision-language model in the Qwen series
- lucataco/qwen3-vl-8b-instruct
modelrecord2,866,532 downloads/month
- text-generation
Task: text-generation
- text-generation
modelrecord26,675 downloads/month
- image-text-to-image
Task: image-text-to-image
- image-text-to-image
modelrecord
- qwen/qwen3-235b-a22b-instruct-2507
Updated Qwen3 model for instruction following
- qwen/qwen3-235b-a22b-instruct-2507
modelrecord725,920 downloads/month
- any-to-any
Task: any-to-any
- any-to-any
- 10Qwen3 VL Demodemo or tutorialno passport yet
MCP serverrecord
- Qwen3_VL_Demo__lambda__1
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.