LM Studio
Free tierRun AI models locally and privately on your own hardware
Key strengths
Facts verified against lmstudio.ai on
Recent changes
- Plans updated: Free plan ($0) includes local LLMs, Bionic Agent, offline voice transcription, LM Link for up to 5 devices, and limited web search. Bionic+ is $20/month with US-hosted open source models and web search. Pro is $100/month with 5× usage limits and early access to new features. Team/organization billing available.
- Models updated: Local open models (llama.cpp, MLX) and US-hosted open source models (Kimi K3, GLM 5.3, DeepSeek V4 Flash/Pro, GLM 5.2)
Get alerts when LM Studio changes
Free. We'll email you when pricing, the free tier, API access or open-source status changes.
Documentation & Developer Resources
LM Studio provides a local API that developers can target for LLM inference, making it a drop-in local backend for AI-powered applications. The platform supports both fully offline deployments and hybrid setups that optionally route to US-hosted open source models (with Zero Data Retention).
What developers should know:
- Local API: Available for programmatic integration with local LLM inference
- Inference backends: llama.cpp (broad hardware support) and MLX (optimized for Apple Silicon)
- Supported hosted models: Kimi K3, GLM 5.3, DeepSeek V4 Flash/Pro, GLM 5.2
- Self-hosting: Fully supported; the application can run entirely offline
- Open source: Source code is publicly available on GitHub (5,359 stars)
- Device connectivity: LM Link enables multi-device access (up to 5 devices on free tier)
- Agentic runtime: Bionic Agent layer handles tool use, computer control, and task orchestration
Developers building privacy-sensitive applications or needing local inference for air-gapped or low-latency environments will find the llama.cpp/MLX stack and local API particularly relevant. The optional ZDR cloud tier provides a path to scaling with hosted frontier models without compromising on data retention policies.