Local models
AI programs that run on your own computer, not on the internet.
Local models are AI programs that you can run directly on your personal computer or device. This means the AI processing happens on your hardware, not on remote servers accessed through the internet.
This is different from cloud-based AI services like ChatGPT or Google Gemini, where your requests are sent to powerful computers owned by the company. Running models locally can offer more privacy, faster responses for certain tasks, and the ability to use AI even without an internet connection.
Local models are AI systems, typically large language models (LLMs) or diffusion models, that are deployed and executed on a user's local hardware rather than on cloud infrastructure. This approach bypasses the need for constant internet connectivity and API calls to remote servers, potentially reducing latency and data transfer costs. Tradeoffs include hardware limitations, requiring significant computational resources (GPU, RAM) for larger models, and the user's responsibility for setup and maintenance.
Local models are gaining traction as companies like Microsoft aim to integrate more AI processing directly onto personal computers. This shift allows for more demanding AI tasks to be handled on the device itself, improving user experience and potentially privacy.
- Microsoft looks to reboot the AI PC with NvidiaMicrosoft · Axios AI ·
- 9 AI Techniques You Probably Haven't TriedOpenAI · The AI Daily Brief ·
- Microsoft Copilot
- Microsoft is pushing for AI PCs that offer local processing power for demanding AI tasks.
- OpenAI ChatGPT
- OpenAI's work on advanced AI techniques implies potential applications that could eventually run locally, beyond basic prompting.
- Cloud AI
- Cloud AI runs on remote servers accessed via the internet, while local
- API
- An API is a way for programs to communicate, often used to access cloud AI,
- Embedded AI
- Embedded AI is AI integrated into a device, often for specific func
The concept of running AI models locally predates modern LLMs, with early machine learning algorithms often executed on personal machines. The term gained prominence with the rise of powerful open-source models that could be downloaded and run by individuals.
Download and install a user-friendly interface for running local LLMs, such as LM Studio or Ollama. Then, download a small, open-source model (e.g., a quantized version of Llama 3) and interact with it through the application's chat interface.
The Playbook: reusable how-tos, prompts, configs and tips pulled out of the news.
- PromptRole-play a student struggling with math for AI tutor simulationSimulate a student's math struggles and uncertainty for AI tutor evaluation. · 5 min
- TemplateReusable workflow templates for healthcare teamsTeams can create and share templates for common workflows like documentation or prior authorizations. · 15 min
- TemplateTemplate for building an AI tool tailored to your workA structured approach to defining and building a custom AI tool for specific business needs. · 15 min
- TemplateEvals CSV prompt list for agent skillsA CSV file template for listing prompts used in evaluating agent skills. · 20 min
- HeuristicDouble coding agent task completion with docs linksProviding coding agents with a documentation link significantly increases their task completion rate. · 2 min
Questions people ask
- Is local AI better than cloud AI?
- It depends on your needs. Local AI offers more privacy and offline use, while cloud AI often provides access to more powerful, up-to-date models and requires less powerful hardware.
- Do I need a powerful computer for local AI?
- Yes, running larger or more capable local AI models typically requires a computer with a strong processor, ample RAM, and often a dedicated graphics card (GPU).
First seen on Subvolts Aug 20, 2026. Updated Oct 14, 2026. Written by an AI model from the items above and reviewed against them weekly; report an error.