7 actions in 7 pieces of software · ranked by words, meaning and measured trust · 503 ms
modelrecord234,548 downloads/month
- image-text-to-text
Task: image-text-to-text
- image-text-to-text
modelrecord88,393 downloads/month
- text-generation
Task: text-generation
- text-generation
modelrecord45,669 downloads/month
- any-to-any
Task: any-to-any
- any-to-any
- 4Qwen3.8-27B Chatdemo or tutorialno passport yet
MCP serverrecord
- qwen3_8_27b_chat_generate
Chat with Qwen3.8-27B (4-bit, ZeroGPU) and stream the reply.
- qwen3_8_27b_chat_generate
modelrecord
- lucataco/qwen3-embedding-8b
The Qwen3 Embedding model series is specifically designed for text embedding and ranking tasks
- lucataco/qwen3-embedding-8b
modelrecord
- lucataco/qwen3-vl-8b-instruct
A powerful vision-language model in the Qwen series
- lucataco/qwen3-vl-8b-instruct
modelrecord
- tejasunku/qwen3-reranker-8b
Rerank query search results using qwen3 reranker 8b model, with support for instructions
- tejasunku/qwen3-reranker-8b
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.