Instead of Claude and Anthropic models, I use my local LLMs for coding (and not vibe-coding, mind you)
xda-developers.com
Search
Self-hosted LLMs are way more powerful than a chat interface, here’s how I utilize it fully
…Sign in to your XDA account Self-hosting your own LLM is usually born out of a desire for two things: absolute privacy and total control. You set up the hardware, pull…
Claude Code with a local LLM running offline is the hybrid setup I didn't know I needed
xda-developers.com
I started using my local LLMs and an MCP server to manage my NAS – it's surprisingly powerful (and safe)
…Credit where it’s due, the developer has also included extra provisions to ensure LLMs don’t randomly execute destructive actions on their own. Setting it up was pretty easy, and all…
I tried caring about ChatGPT and Claude, but I still haven't found a real need for LLMs
…Sign in to your XDA account I'd be lying if I said I don't touch any LLMs throughout the day. I'm not big on using AI on every device…
My local LLM rewrote my resume better than ChatGPT, and it's not even close
xda-developers.com
Ollama is still the easiest way to start local LLMs, but it's the worst way to keep running them
…In my spare time, you’ll probably find me playing Counter-Strike or VALORANT, and you can reach out to me at adam@xda-developers.com , on Twitter as @AdamConwayIE , on Instagram…
One tiny change made my local LLMs more useful than ChatGPT for real work
…Sign in to your XDA account As much as I adore my local LLMs, they can’t hold a candle to the reasoning capabilities of their cloud counterparts, and for good reason…
Local LLMs work best when you're not loyal to just one
xda-developers.com
Stop obsessing over your GPU's core clock — memory clock matters more for local LLM inference
xda-developers.com