Self-hosted alternatives to LM Studio
Want to run large language models on your own hardware with open-source software instead of LM Studio? These 4 self-hostable apps run models locally or on your own server.
About LM Studio: Closed-source desktop app for downloading and running large language models on your own computer.
| App | Health | Stars | License | Docker | RAM (est.) | From |
|---|---|---|---|---|---|---|
| Ollama | Active | 186.9k | MIT | ✓ | 8 GB | $40/mo |
| AnythingLLM | Active | 68.3k | MIT | ✓ | 8 GB | $40/mo |
| LocalAI | Active | 50.4k | MIT | ✓ | 8 GB | $40/mo |
| LLM Harbor | Active | 3.3k | Apache-2.0 | ✓ | 8 GB | $40/mo |
The options in detail
1. Ollama
Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, and other large language models.
Active Last commit 2026-11-09. 10+ releases in the past year. Latest release v0.40.16 (2026-11-09). Needs roughly 8 GB RAM. How to run it →
2. AnythingLLM
All-in-one desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.
Active Last commit 2026-11-09. 10+ releases in the past year. Latest release v1.19.0 (2026-10-26). Needs roughly 8 GB RAM. How to run it →
3. LocalAI
Run your AI models locally and generate images and audio (alternative to OpenAI and Claude).
Active Last commit 2026-11-10. 10+ releases in the past year. Latest release v4.12.1 (2026-10-23). Needs roughly 8 GB RAM. How to run it →
4. LLM Harbor
Containerized LLM toolkit. Run LLM backends, APIs, frontends, and additional services via a concise CLI.
Active Last commit 2026-10-31. 10+ releases in the past year. Latest release v0.5.19 (2026-10-31). Needs roughly 8 GB RAM. How to run it →
Browse related categories
Other alternatives guides
LM Studio is a trademark of its owner; this site is not affiliated with it. Listings come from the community-maintained awesome-selfhosted list.