tool

KTransformers

Runs large mixture-of-experts models with CPU-GPU heterogeneous inference and an OpenAI-compatible server.

What it provides

LLM servingCPU/GPUOpenAI API

Connect an HTTPS inference API. Model weights stay on CPU/GPU infrastructure and are never installed inside the 4 GB bot.

Connection requirements

A KTransformers inference server behind HTTPS

Protocol
OpenAI-compatible REST
Endpoint
https://ktransformers.example.com
Authentication
Choose the mode required by your service
Example callsget /v1/modelspost /v1/chat/completions {"model":"MODEL_ID","messages":[{"role":"user","content":"Hello"}]}
Open official setup guide ↗

Where to add it

Open Dashboard Tools, select a running OpenClaw or Hermes instance, then use the card’s Install or Connect action. External services may require an HTTPS endpoint and credentials; the dashboard shows those fields before anything is saved.

Related Models & routing