How to Install Local AI Models on Mac (Easy Tutorial)

2 Просмотры

Спасибо! Поделитесь с друзьями!

Вам не понравилось видео. Спасибо за то что поделились своим мнением!

Издатель Oct 3, 2026

Discover how to easily install local AI models on your Mac for FREE !

Step 1 Install Ollama on macOS
Before you can run any models, you need the Ollama engine installed to manage them. The easiest way to install it on a Mac: just Go to https://ollama.com

Step 2: Install AI model based on your RAM

For 8GB RAM
run qwen:3b

For 16GB Macs, use
ollama run deepseek-r1:7b

For 36GB Macs, use
ollama run deepseek-r1:14b

or

ollama run qwen3.5:35b

For 48GB Macs, use
ollama run deepseek-r1:32b

or

ollama run qwen3.5:35b

for 64GB Macs, you can run
ollama run llama3.1:70b

Setting Up a Web Interface (Open WebUI)
INSTALL DOCKER DESKTOP
Open WebUI runs inside a lightweight container, which requires Docker to be installed on your Mac.
Go to the official Docker website and download Docker Desktop for Mac www.docker.com

Open Docker Desktop from your Applications folder. You may be prompted to enter your Mac's password to grant system permissions.
Verify: Wait until the whale icon in your menu bar turns green and says "Docker Desktop is running."

With Ollama and Docker already running on your Mac, open your terminal and run the following command to download and start the web interface:

docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main

CHAT IN SAFARI
Open Safari (or your preferred browser).
Navigate to http://localhost:3000/.

✅ Subscribe to get the most out of your Apple Devices: @ArthurBrs777