30-SECOND SUMMARY
What to take away
- LM Studio currently requires Apple Silicon on macOS; Windows x64 requires AVX2.
- Start with a small instruct model around Q4.
- Downloaded models can run offline, while search, downloads, and updates require a network.
Run the first model
A small, repeatable baseline is the goal.
- 01DISCOVER
Check model and license
- 02DOWNLOAD
Start around Q4
- 03LOAD
Leave memory headroom
- 04CHAT
Use fixed test prompts
Check system requirements
Official requirements list Apple Silicon and macOS 14 or later for Mac; Intel Macs are not supported. Windows x64 systems require AVX2. LM Studio recommends 16GB or more RAM.
An 8GB Mac can test smaller models with modest context, but it should not be presented as a universal minimum.
Choose a model in Discover
Search for an instruct model and inspect the publisher, model card, license, parameter size, and GGUF quantization. LM Studio recommends 4-bit or higher when the machine can support it.
Start with one 3B–8B model rather than downloading many variants at once.
Load and test
After download, select the model in Chat and load it into memory. Ask short, verifiable questions before increasing context or adding documents.
If loading fails, close other applications, reduce context, and try a smaller model or quantization.
Verify offline operation
Official documentation states that downloaded models, chats, document conversations, and the local server can work offline. Model discovery, downloads, and updates need the network.
Test the exact workflow with connectivity disabled before relying on it for sensitive material.
Use the local API carefully
The Developer view or `lms server start` can expose an API at localhost:1234. Keep the first application local to the same computer.
Configure authentication and network controls before binding to external interfaces.
lms server start
# Default local address
http://localhost:1234Frequently asked questions
Can LM Studio run on an Intel Mac?
The current official requirements say Intel Macs are not supported.
Is 8GB RAM enough?
It can test small models with short context, but 16GB or more is the official recommendation.
Do I also need Ollama?
No. Start with one runtime; choose LM Studio for a GUI or Ollama for terminal and API workflows.
Primary sources
Check the original documentation for version-specific details.