XXORTRONLARGE PLAYGROUND
Not connected
MISTRAL ARCHITECTURE / 123B PARAMETERS

A little curiosity.
A lot of compute.

Explore XORTRON Large through conversation.
Connect your model endpoint and see where a question takes you.

2026.3Streaming responsesModel card ↗
Connect an endpoint to start. No model is running in this Space.

Connect your model

This playground uses your own OpenAI-compatible endpoint. Your messages go directly to that server.

The server must allow browser requests (CORS) and serve this exact model. No hosted inference provider is currently listed on the model card.

Generation settings

Lower for focused answers, higher for more variety. Zero uses greedy decoding.

Changes apply to your next message. Long conversations may exceed the endpoint's context limit; start a new chat if needed.