This is going to be a very personal question, because when you’re talking cloud vs local anything, it comes down to this: how much are you willing to pay for independence? The local option might save you long term, or it might never pay off the capital investment. It will almost certainly cost you your time to set up and maintain your own system — but what you get back is independence. With LLMs, traditionally you lose quite a bit of performance, but as [Anurag Singh] points out on XDA Developers, a lesser model might actually let you get more done, depending on your workflow.

[Anurag] had been on the 20$/month plan with Anthropic when he decided that the scratch just wasn’t worth the sniff– he was hitting usage limits he couldn’t stand at that level, but couldn’t justify a higher tier of access. So he decided to try a local LLM, even though all he had was a 16 GB MacBook Air M5, not a beefy workstation. Since his workflow isn’t so much ‘vibe code the whole thing for me’ as ‘help me find where I went wrong here, electronic rubber duck’, Qwen2.5 Coder 14B proved more than adequate for his use case.

It can’t understand all the moving parts of a large project as well as Claude can — not surprising given how old it is and how much memory it has to work with — but that’s [Anurag]’s job. He’s the programmer, it’s just the assistant. For his use case, he can make use of his existing hardware and having the the LLM right in VS Code is allows for a speedy workflow.

Your millage may vary, but if you want to get into locally running LLMs, we can point you at the easy ways to get started. Depending on your hardware, you might want to grab another GPU.

The odds are, you have a device deliberately designed to be addictive in your pocket or on the table next to you if you aren’t staring at it right now– your smartphone. We’ve seen a number of projects that try and help people control or moderate their phone usage using a variety of techniques; this vitual pet by [brenpoly] does it by weaponizing human empathy, and our bizzare ability to pack-bond with literally anything.

The virtual pet itself is based on an ESP32 in a cutesy 3D-printed case, and we think it would probably work well enough if it just had hard-coded behaviors based on hooks in what you’re doing on your phone– the “my little buddy is sick because I’m doomscrolling” should be effective enough on its own, and that part is hardcoded on the ESP32 along with the regular virtual pet behaviour–but this is the year of our Llama 2026, so there has to be an LLM in there somewhere, right?

Some people would leave this part out, but we think [brenpoly]’s use of a local LLM on the phone does improve the project. The local agent doesn’t just have access to his screen time, but his notifications, too, and runs a whisper model linked to a microphone in the virtual pet via bluetooth. So you can get the contents or a summary of your notifications without looking at your phone, or just ask the little guy to tell you a joke. Giving the pet a voice with a the local piper model is also more effective at getting you to put your phone down when you hit the limits.

They’ve put the whole thing up on GitHub if you want to make your own– and if we can keep one person from strapping themselves to a shock collar, then this project is doing good in the world. If helps [brenpoly] or any of his fans do less scrolling and more hacking, that’s even better. Of course there’s a whole spectrum between “electrocute yourself” and “lovable virtual pet” when it comes to controlling your phone use, a spectrum that includes phone stands or even smart vaults for your device.

Thanks to [brenpoly] for the tip! Remember, all of your doomscrolling is justified if you find something to send to our tipsline.