LM Studio
by Various
Run local AI models like gpt-oss, Llama, Gemma, Qwen, and DeepSeek privately on your computer.
Apps
LM Studio
Added 1 June 2026
Overview
LM Studio is a desktop application that lets you run large language models like Llama, Gemma, Qwen, and DeepSeek entirely on your own computer. It supports a range of open-source models and operates without sending data to external servers.
Best for
Best for
Developers and privacy-conscious users who want offline access to open-source LLMs without cloud dependency
Use cases
- Running LLMs offline for privacy-sensitive tasks without internet dependency
- Experimenting with different open-source models locally for testing or prototyping
- Using AI assistance for document analysis or coding without API costs
Notes
LM Studio is a desktop application that lets you run large language models like Llama, Gemma, Qwen, and DeepSeek entirely on your own computer. It supports a range of open-source models and operates without sending data to external servers.
Use cases
- Running LLMs offline for privacy-sensitive tasks without internet dependency
- Experimenting with different open-source models locally for testing or prototyping
- Using AI assistance for document analysis or coding without API costs
Pros
- Full privacy: all inference happens locally, no data leaves your machine
- No recurring API or subscription fees after initial setup
- Supports a wide variety of popular open-source model families
Cons
- Requires a powerful GPU and sufficient RAM to run larger models smoothly
- Local inference can be slower than cloud-hosted alternatives
- Only works with models you can download and fit on your hardware
Indexed from awesome-generative-ai and enriched against its public facts.
Pros
- Full privacy: all inference happens locally, no data leaves your machine
- No recurring API or subscription fees after initial setup
- Supports a wide variety of popular open-source model families
Cons
- Requires a powerful GPU and sufficient RAM to run larger models smoothly
- Local inference can be slower than cloud-hosted alternatives
- Only works with models you can download and fit on your hardware
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.