# Local model

Concept · [Building with AI](https://ecosystem.samcarlton.com/ai)

Also called: local models, running models locally, run locally, run a model locally, local AI, local LLM, on-device model, self-hosted model, offline model

A model that is downloaded and run on a person's own computer or a company's own [servers](https://ecosystem.samcarlton.com/server), not on a provider's. The data stays on that machine, and speed depends on its [hardware](https://ecosystem.samcarlton.com/hard-tech).

**For example:** A [developer](https://ecosystem.samcarlton.com/software-engineer) downloads an [open-weight model](https://ecosystem.samcarlton.com/open-source-vs-open-weights) and runs it on a desktop computer with a strong [GPU](https://ecosystem.samcarlton.com/gpu). The [prompts](https://ecosystem.samcarlton.com/prompt) never leave the building.

## Connects to (20)

- [Weights](https://ecosystem.samcarlton.com/weights): The numbers inside a model that it learned during training.
- [GPU](https://ecosystem.samcarlton.com/gpu): Graphics processing unit.
- [Open source vs open weights](https://ecosystem.samcarlton.com/open-source-vs-open-weights): Two labels for AI models that people often mix up.
- [Inference](https://ecosystem.samcarlton.com/inference): An AI model producing an answer to a request.
- [Data privacy](https://ecosystem.samcarlton.com/data-privacy): How a company collects, uses, stores and shares information about people.
- [Quantization](https://ecosystem.samcarlton.com/quantization): Shrinking a model by storing its weights with fewer digits of precision.
- [Apple Silicon](https://ecosystem.samcarlton.com/apple-silicon): Apple's own family of chips used in Mac computers and iPads.
- [Hugging Face](https://ecosystem.samcarlton.com/hugging-face): A platform where the machine learning community shares AI models, datasets and demo apps.
- [Model provider](https://ecosystem.samcarlton.com/model-provider): The company or service that runs an AI model and answers requests to it, usually over the internet through an API.
- [Llama](https://ecosystem.samcarlton.com/llama): Meta's family of AI models whose weights are published for download.
- [Gemma](https://ecosystem.samcarlton.com/gemma): Google's family of open-weights AI models, small enough that some run on a laptop or phone.
- [FunctionGemma](https://ecosystem.samcarlton.com/functiongemma): A small Gemma model from Google tuned to turn plain requests into function calls, so an app or device can act on what a person asks.
- [Google AI Edge Gallery](https://ecosystem.samcarlton.com/google-ai-edge-gallery): A free Google app for phones that downloads open AI models and runs them on the device, with no internet connection needed after download.
- [Apple Foundation Models](https://ecosystem.samcarlton.com/apple-foundation-models): Apple's on-device AI model and the framework that lets app developers use it on iPhone, iPad and Mac.
- [LM Studio](https://ecosystem.samcarlton.com/lm-studio): A free desktop app for downloading open AI models and running them on a person's own computer, with a chat window and a local API.
- [SQLite](https://ecosystem.samcarlton.com/sqlite): A small, free database that keeps everything in a single file and runs inside the app itself, with no separate server.
- [ONNX](https://ecosystem.samcarlton.com/onnx): An open file format for AI models, so a model trained with one tool can run with another, on servers, phones or in a browser.
- [Superwhisper](https://ecosystem.samcarlton.com/superwhisper): A speech-to-text app for computers and phones.
- [MacWhisper](https://ecosystem.samcarlton.com/macwhisper): A Mac app that transcribes audio and video files and dictation on the computer itself, using open speech models such as OpenAI's Whisper.
- [Hex](https://ecosystem.samcarlton.com/hex-dictation): A free, open-source voice dictation app that turns speech into text on the person's own computer, so audio is not sent to a server.

Map view: https://ecosystem.samcarlton.com/local-model