cloudflareedgellmarchitecture
Cloudflare Workers AI: Running LLMs at the Edge
Cloudflare Workers AI
Traditional: 400–900ms. Workers AI: 50–120ms.
Models available:
@cf/meta/llama-3.1-8b-instruct@cf/mistral/mistral-7b-instruct-v0.1
Traditional: 400–900ms. Workers AI: 50–120ms.
Models available:
@cf/meta/llama-3.1-8b-instruct@cf/mistral/mistral-7b-instruct-v0.1