SyphaChatSyphaChat SetupEmbedder SetupLocal
LM Studio Embedder
LMStudio supports LLM and embedding GGUF models from HuggingFace that can be run on CPU or GPU.
Screenshot coming soon
LM Studio Embedder
Heads up!
LMStudio's inference server only allows you to load multiple LLMs or a single embedding model, but not both. This means LMStudio cannot be both your LLM and embedder.
LMStudio supports LLM and embedding GGUF models from HuggingFace that can be run on CPU or GPU.
LMStudio is a separate application that you need to download first and connect to.
Connecting to LM Studio
When running LMStudio locally, you should connect to LMStudio by first running the built-in inference server.
You must explicitly load the embedding model before starting the inference server.
You can update your model to a different model at any time in the Settings.
Screenshot coming soon