minus-squareprojectmoon@lemm.eetoOpen Source@lemmy.ml•How to run LLaMA (and other LLMs) on Android.linkfedilinkarrow-up3·20 days agoIt’s enough to run quantized versions of the distilled r1 model based on Qwen and Llama 3. Don’t know how fast it’ll run though. linkfedilink
It’s enough to run quantized versions of the distilled r1 model based on Qwen and Llama 3. Don’t know how fast it’ll run though.