Back to Directory
Overview
LM Studio is a powerful desktop application that allows you to easily find and run local models from Hugging Face. It features a full chat interface and a local server that mimics OpenAI's API.
Capabilities & Support
text
vision
audio
image
video
Popular Models
| Model Name | Type | Size | Best For |
|---|---|---|---|
| Qwen 2.5 | text | 0.5B - 72B | Alibaba's top-tier open models, great for coding and math. |
| Llama 3.1 GGUF | text | 8B, 70B | The most popular base for local LLMs in GGUF format. |
| Moondream 2 | textvision | 1.6B | Tiny but efficient vision model for image captioning. |
Installation Guide
1
Download Installer
Visit lmstudio.ai and download the version corresponding to your hardware (Intel, Apple Silicon, etc.).
2
Search for a Model
Open LM Studio and use the search icon on the left to find models. We recommend starting with 'Llama-3-8B-Instruct-GGUF'.
3
Download & Load
Select a quantization (4-bit or 8-bit usually works best) and click Download. Once done, go to the AI Chat tab and select the model at the top.