Local LLMs changed how I use Home Assistant, and now my smart devices actually listen
… After all, few things can match the convenience of an LLM-controlled Home Assistant. …
Search
Self-hosted LLMs are way more powerful than a chat interface, here’s how I utilize it fully
… While a standard chat waits for your input, AgenticSeek uses your local LLM to actually do things. By treating the LLM as an API for these agents, I can offload entire workflows. …
I connected my local LLM to Home Assistant through MCP, and now my smart home manages itself
… Sign in to your XDA account I’ve started pairing my FOSS applications with self-hosted LLMs running on my Ollama and LM Studio instances, and AI-powered workflows have made my life a lot smoother. …
Home Assistant's local LLM support outperforms Gemini for Home, and Google knows it
… Related I don't pay for ChatGPT, Perplexity, Gemini, or Claude – I stick to my self-hosted LLMs instead There's no point in relying on AI tools when my local LLMs can handle everything Home Assistant with a local LLM is already doing what Gemini for Home promises Run your stack with your rules You … …
I tried caring about ChatGPT and Claude, but I still haven't found a real need for LLMs
… Related Your local LLM feels weak because you're treating it like a search engine It’s not the model’s fault Invisible AI is the inevitable future, and that's what I'm waiting for LLMs, whether cloud or local, have transformed the workflows of many of my fellow writers, but I'm not convinced yet. …
I’d do these 5 things differently if I started self-hosting LLMs today
… Related 5 self-hosted LLMs I use for specific tasks My customized, self-hosted AI workflow Focus on workflow integration instead Connecting the engine to the wheels For a long time, my local LLM was just a destination, a tab I’d visit when I had a specific question. …
I thought I needed a GPU for local LLMs until I tried this lean model
… If you are still not convinced about local LLMs, check out these obvious advantages of using them over cloud AI .
Self-hosted AI may not be for everyone, but I'm done paying for ChatGPT and other cloud models
… Related I ran local LLMs on a "dead" GPU, and the results surprised me My Pascal card may not be ideal for intensive workloads, but it's more than enough for light LLM-powered tasks My local AI-aided workflows insulate me on the privacy front Although the fact that I don’t have to pay monthly subsc… …
Local LLMs work best when you're not loyal to just one
… Not all LLMs are created equal The “best LLM” depends entirely on your use case If you lurk in AI-centric forums, you’ve probably come across posts highlighting specific LLMs as the next best thing since sliced bread. …
I started using my local LLMs and an MCP server to manage my NAS – it's surprisingly powerful (and safe)
… And I don’t just mean cloud-based LLMs, either. I’ve spent the last couple of months pairing my local models with open-source tools, and these LLMs are surprisingly good at tackling OCR workflows, generating bookmark tags, organizing notes, and other bogus tasks. …