On: Ask HN: What would you preserve if the internet we...

[tarruda]

> Download as many LLM models and the latest version of Ollama.app and all its dependencies.

I recently purchased a Mac Studio with 128gb RAM for the sole purpose of being able to run 70b models at 8-bit quantization

[FloatArtifact → tarruda]

M4?

[mikestew → FloatArtifact]

Mac Studios don't have the M4 yet. With that much RAM, GP must have the M2 Ultra.

[867-5309 → tarruda]

well done, good for you!