This model is from our Model Catalog, and comes with pre-configured recipes. Deployment has been verified by Hugging Face.
Use the hf CLI or connect our MCP server so your AI assistant can manage your endpoints directly, then copy a prompt for it to deploy this model.
Balances answer speed and capacity, so one endpoint copes with varied requests.
Measured Oct 22, 14:47 UTC at 64 concurrent requests of about 2,048 input and 256 output tokens — the heaviest measured load that still met every target.
This Catalog Recipe comes with a pre-configured vLLM engine.
Default Env values come from the Catalog Recipe and can't be edited during Endpoint creation.