Ollama | Easiest way to run Local LLM on mac and linux
📅 Book a 1:1 with me (AI + cloud, 60 min) → https://cloudyeti.io/meet?utm_source=...
🎓 Harness Engineering course → https://learn.cloudyeti.io/courses/ha...
🎓 Claude Code for Creators course → https://learn.cloudyeti.io/courses/cl...
🖥️ LOCAL AI HARDWARE (affiliate links)
NVIDIA DGX Spark 128GB (GB10 Grace Blackwell): https://amzn.to/4wKSmfY
ASUS Ascent GX10 (DGX Spark class, GB10 128GB): https://amzn.to/45dSQPS
AMD Ryzen AI Halo desktop (Linux dev box): https://amzn.to/4z5QQqk
MacBook Pro M5 Max 128GB: https://amzn.to/4z0ZuGR
Mac Studio M4 Max 128GB: https://amzn.to/4deA3Zu
MacBook Pro M-series 24GB (entry tier): https://amzn.to/497Q6Ww
EVGA RTX 3090 24GB (budget local AI GPU): https://amzn.to/3QJztKW
GIGABYTE RTX 5090 32GB: https://amzn.to/3SLTh0U
As an Amazon Associate I earn from qualifying purchases (at no extra cost to you).
Get up and running with large language models, locally with OLLaMa
GIthub repo: https://github.com/jmorganca/ollama
Website: https://ollama.ai/
Notes:
The easiest way to run local LLMs. We’ll find out.
Currently only Mac and Linux are supported. Windows coming soon
Commands:
ollama run llama2
Questions answered in this video:
How do you install Ollama on macOS?
How do you install and use the Ollama command-line tool?
How do you download and run a local Llama 2 model with one command?
How well does Ollama run on an M2 MacBook Air with 16GB of memory?
Can a local Ollama model generate a working Python script?
How do you download and run Mistral with Ollama?
How do you switch between local models after downloading them?
Work with CloudYeti
Follow along
X: https://x.com/ravsau
LinkedIn: / sauravsharma93
☕ Help me fund a DGX Spark for more local AI videos: https://buymeacoffee.com/cloudyeti
📧 Sponsorship inquiries: [email protected]