Comment by mtmail | Hacker News Reader

Top New Best Ask Show Jobs

Comment by mtmail | Hacker News Reader

I ran the 13GB https://simonwillison.net/2023/Nov/29/llamafile/ on an M3 without issues. 40 tokens per second output.

Thanks. Can you please elaborate on the specs of your computer?

I am planning to buy a mac mini (January 2023) M2 3.49 GHz - SSD 256 GB - 8GB.

https://browser.geekbench.com/macs/macbook-pro-14-inch-nov-2... with 18GB RAM. Simon (the blog author) seems to use 64GB M2 MacBook Pro https://til.simonwillison.net/llms/llama-7b-m2

Reply on news.ycombinator.com