/
#6
LM Studio
Desktop and server app for running open-weight LLMs locally. Supports Llama, Qwen, Gemma, DeepSeek, and Mistral via llama.cpp and Apple MLX backends. Exposes an OpenAI-compatible REST API, Python and TypeScript SDKs, MCP integration, and a headless daemon (llmster) for server and CI deployments. Built-in RAG, structured JSON output, and embeddings.
Categories
Subcategories
MODEL SERVINGINFERENCE OPTIMIZATIONQUANTIZATION
Links
LAST 30 DAYS