lol yeah, it’s a pain. I’ve been using the local llm code interpreter with Mistral, and it’s been okay.
One thing that helped was using a cloud VM for testing before moving everything to my local machine. It’s a bit pricey, but it saves so much time.
Also, check out this blog post on Medium—it’s got some great tips on optimizing performance.
One thing that helped was using a cloud VM for testing before moving everything to my local machine. It’s a bit pricey, but it saves so much time.
Also, check out this blog post on Medium—it’s got some great tips on optimizing performance.