Skip to main contentLM Studio provides a user-friendly way to run AI models locally with privacy, speed, and offline capabilities.
Website: https://lmstudio.ai
Setup
- Download: Visit lmstudio.ai and download for your OS
- Install and launch: Open LM Studio
- Download a model: Go to “Discover” tab and download a model
- Recommended: Qwen3 Coder 30B A3B Instruct for best CodinIT experience
- Start server: Go to “Developer” tab and toggle server to “Running” (runs at
http://localhost:51732)
- Configure model settings:
- Context Length: Set to 262,144 (maximum)
- KV Cache Quantization: Leave unchecked (critical for performance)
- Flash Attention: Enable if available
Configuration in CodinIT
- Click the settings icon (⚙️) in CodinIT
- Select “LM Studio” as the API Provider
- Set server URL to
http://localhost:51732
- Choose your model
Quantization Guide
Choose based on available RAM:
- 32GB RAM: 4-bit quantization (~17GB download)
- 64GB RAM: 8-bit quantization (~32GB download)
- 128GB+ RAM: Full precision or larger models
- Mac (Apple Silicon): Use MLX format
- Windows/Linux: Use GGUF format
Features
- Complete privacy: All data stays on your device
- No API costs: Unlimited free usage
- Offline operation: Works without internet
- Hardware flexibility: Runs on any modern computer
System Requirements
Minimum:
- 8GB RAM (16GB recommended)
- 10GB free storage
- Modern multi-core CPU
Recommended:
- 32GB+ RAM for large models
- NVIDIA GPU with 8GB+ VRAM (optional)
- SSD with 50GB+ free space
Troubleshooting
If CodinIT can’t connect:
- Verify LM Studio server is running
- Ensure a model is loaded
- Check system meets hardware requirements
- Confirm server URL matches in CodinIT settings
Notes
- Start LM Studio before using with CodinIT
- Keep LM Studio running in background
- First model download may take several minutes
- Models are stored locally after download
