Sang Lee posted: For folks running LLMs or diffusion models locally, what models & hardware are you running, and are you happy with the performance?

Posts, a community app by Read.cv

Thread

For folks running LLMs or diffusion models locally, what models & hardware are you running, and are you happy with the performance?

Feb 23, 10:09 PM

Replying to @sang

Ollama + llama2, M2. It’s solid! But def not GPT4.

A community app by Read.cv