I replaced over $1,000 in cloud subscriptions with one small home server
…because StartOS doesn't have GPU passthrough yet and all LLM calculations are handled on the CPU. Minisforum AI X1 Pro-470 CPU AMD Ryzen AI 9 HX 470 Graphics AMD Radeon…
Search
Top stories
I finally stopped forcing local LLMs and switched back to cloud AI
…Ultimately, you might've seen a lot of people running AI models locally on their servers. What most people leave out is that running LLMs locally isn't really for everyone, including…
I stopped trusting cloud AI with my personal files, and switched to this local setup instead
…a cloud AI, it doesn't just get read and discarded. It has to live somewhere while the model processes it, and that somewhere is their infrastructure which is servers you have…
The best NAS distro dropped a public beta for its new update, and it feels more like Proxmox with each release
…I recently set up a Proxmox Backup Server VM inside my local TrueNAS server to store snapshots from my secondary PVE cluster after I ended up choking my primary PBS instance, and…
I turned my phone into a local LLM server, and it handles vision, voice, and tool calls
…agentic workflows, and isn't going to be my primary AI endpoint when I'm sitting at my desk with a GPU nearby. However, it's crazy to think what a phone…
Self-hosted AI may not be for everyone, but I'm done paying for ChatGPT and other cloud models
…Not to mention, the gigantic servers owned by cloud providers can process instructions at breakneck pace, while local AI tools can take anywhere from a few seconds to several minutes when coming…
Ollama is still the easiest way to start local LLMs, but it's the worst way to keep running them
…s cloud servers B To run large language models locally on your own hardware C To fine-tune models using cloud GPU clusters D To create a marketplace for AI model licensing…
I ditched Claude for Obsidian and a local LLM, and miss it less than I expected to
…is what you'd expect when one model runs on Anthropic's servers and the other runs on my GPU. But Opus is overkill for day-to-day chatting anyway, a local…
Trying to self-host LLMs made me realize local AI has a friction problem, not a quality problem
…Your GPU's VRAM limitations might end up crippling performance. Again, this is an example of all the complexity coming before the value. With cloud AI, you get value immediately, and the…
Running local LLMs every day for five months broke every assumption I had about them
…There are documents I’d rather not hand to Google, OpenAI, or Anthropic’s servers now, and once the local AI setup was working , reaching for it in those cases made obvious…