10 actions in 9 pieces of software · ranked by words, meaning and measured trust · 544 ms
modelrecord38,624 downloads/month
- image-text-to-text
Task: image-text-to-text
- image-text-to-text
modelrecord67,779 downloads/month
- text-generation
Task: text-generation
- text-generation
modelrecord
- meta/llama-4-scout-instruct
A 17 billion parameter model with 16 experts
- meta/llama-4-scout-instruct
modelrecord
- meta/llama-4-maverick-instruct
A 17 billion parameter model with 128 experts
- meta/llama-4-maverick-instruct
modelrecord
- llama-3.1-nemotron-70b-instruct
Task: Llama-3.1-Nemotron-70B-Instruct
- llama-3.1-nemotron-70b-instruct
modelrecord
- llama3.1-8b-instruct
Task: Llama3.1-8b-instruct
- llama3.1-8b-instruct
modelrecord
- gh200-144g-hbm3e
Task: GH200 144G HBM3e
- a10g
Task: A10G
- gh200-144g-hbm3e
modelrecord
- llama3-8b-instruct
Task: Llama3-8b-instruct
- llama3-8b-instruct
modelrecord
- llama3.1-405b-instruct
Task: Llama3.1-405b-instruct
- llama3.1-405b-instruct
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.