rich1.0TheGuySwann wroteTheGuySwann (npub1h8…6rpev)https://yabu.me/npub1h8nk2346qezka5cpm8jjh3yl5j88pf4ly2ptu7s6uu55wcfqy0wq36rpevnjumphttps://yabu.meVenice.ai and select the llama3.1 model. Great option for a big model that you can’t run locally.
Otherwise a local llama3.1 20B is solid if you have the RAM