← Back to Blog

Use your LM Studio Models in Claude Code

By
LM Studio Team

•

2026-01-30

With LM Studio 0.4.1, we're introducing an Anthropic-compatible /v1/messages endpoint. This means you can use your local models with Claude Code!

undefined

LM Studio and Claude Code

First, install LM Studio from lmstudio.ai/download and set up a model.

Alternatively, if you are running in a VM or on a remote server, install llmster:

curl -fsSL https://lmstudio.ai/install.sh | bash

1) Start LM Studio's local server

Make sure LM Studio is running as a server. You can start it from the app, or from the terminal:

lms server start --port 1234

2) Point Claude Code at LM Studio

Set these environment variables so the claude CLI talks to your local LM Studio server:

export ANTHROPIC_BASE_URL=http://localhost:1234
export ANTHROPIC_AUTH_TOKEN=lmstudio

3) Run Claude Code in your terminal

From the terminal, use:

claude --model openai/gpt-oss-20b

That's it! Claude Code is now using your local model.

We recommend starting with a context size of at least 25K tokens, and increasing it for better results, since Claude Code can be quite context-heavy.

Alternatively: Configure Claude Code in VS Code

Open your VS Code settings:

"claudeCode.environmentVariables": [
  {
    "name": "ANTHROPIC_BASE_URL",
    "value": "http://localhost:1234"
  },
  {
    "name": "ANTHROPIC_AUTH_TOKEN",
    "value": "lmstudio"
  }
]
undefined

Use your GGUF and MLX local models with Claude Code

Under the Hood

LM Studio 0.4.1 provides an Anthropic-compatible /v1/messages endpoint. This means any tool built for the Anthropic API can talk to LM Studio with just a base URL change.

What's supported

  • Messages API: Full support for the /v1/messages endpoint
  • Streaming: SSE events including message_start, content_block_delta, and message_stop
  • Tool use: Function calling works out of the box

Python example

If you're building your own tools, here's how to use the Anthropic Python SDK with LM Studio:

from anthropic import Anthropic

client = Anthropic(
    base_url="http://localhost:1234",
    api_key="lmstudio",
)

message = client.messages.create(
    max_tokens=1024,
    messages=[
        {
            "role": "user",
            "content": "Hello from LM Studio",
        }
    ],
    model="ibm/granite-4-micro",
)

print(message.content)

Troubleshooting

If you're running into issues:

  • Check that the server is running: Run lms status to verify LM Studio's server is active
  • Verify the port: Make sure ANTHROPIC_BASE_URL uses the correct port (default: 1234)
  • Check model compatibility: Some models work better than others for agentic tasks

Still stuck? Hop onto our Discord and ask in the developers channel.

Resources