LM Studio — Local inference with a GUI
LM Studio is a desktop app that runs LLMs locally with an OpenAI-compatible API. Decoder targets that endpoint when you choose local inference.
What it is
Local LLM runtime with a GUI and an OpenAI-compatible HTTP server.
Why it's useful
Zero data egress, no API key, runs on your laptop.
How Decoder implements it
Set the local endpoint in Settings; Decoder routes AI calls to LM Studio.
When to use it
Confidential code, offline work, cost-free experimentation.
When NOT to use it
When you need frontier-model quality on a thin laptop.
Practical example
Run Qwen2.5-Coder in LM Studio; Decoder's Explain uses it without ever calling the cloud.
FAQ
Glossary
- OpenAI-compatible
- An HTTP API mirroring OpenAI's chat/completions shape.
Related
Local AI lets you use Decoder's explain and chat features against a model running on your own hardware via Ollama or LM Studio — useful when code cannot leave your environment.
Ollama is a lightweight runtime for serving open-weight LLMs locally. Decoder talks to it through its OpenAI-compatible endpoint.
BYOK means you bring your own AI provider key. Decoder never proxies AI calls through a shared account: your key, your billing, your privacy boundary.