Post

Simon Willison
@simonwillison.net

I can now run a GPT-4 class model on my laptop (The exact same laptop that could just about run a GPT-3 class model 20 months ago) The new Llama 3.3 70B is a striking example of the huge efficiency gains we've seen in the last two years simonwillison.net/2024/Dec/9/l...

simonwillison.netI can now run a GPT-4 class model on my laptopMeta’s new Llama 3.3 70B is a genuinely GPT-4 class Large Language Model that runs on my laptop. Just 20 months ago I was amazed to see something that felt …
John Capobianco
@handle.invalid

Is Llama3.3 via Ollama better at Agentic work ? I’ve only had success with ChatGPT4o whenever I try my agents with llama it seems to do its own thing and ignore the tools

Simon Willison
@simonwillison.net

I haven't tried tool use with it yet - Ollama has that as a feature now, would be interesting to explore

0 reposts1 like

Mahdi Yusuf
@mahdiyusuf.com

I have tried it, it's hit and miss even with the large models. I hopeful it's going to get better. many instances of it not honouring parameters and or not using the response from the tool when it does work.

John Capobianco
@handle.invalid

Thank you ! I have a few agents and a tag implementation but have I’d love to make totally free and open but the tool calling / Agentic stuff hasn’t quite gotten there yet