$ cat ~/notes
Field notes from building products end-to-end - fullstack TypeScript, self-hosted infra, and the occasional foray into local LLM inference. Mostly things I wish I'd known six months ago.
⌘K
$ cat post.md ───────────────── # how-i-built-a-self-hosted-ai-chat-for-my-portfolio-with-llama-cpp-and-gemma tags: [self hosted LLM, portfolio AI assistant, CPU inference, local LLM inference, Vercel AI SDK, Next.js AI chatbot, Gemma portfolio chat, llama.cpp tutorial] read: ~1min
★ FEATURED · LATEST
How I Built a Self Hosted AI Chat for My Portfolio with llama.cpp and Gemma
A practical walkthrough of running a local LLM on modest hardware, wiring it to a Next.js portfolio with the Vercel AI SDK, and the gotchas nobody warns you about.
JUN 09, 2026·1 min read·#self hosted LLM #portfolio AI assistant #CPU inference #local LLM inference #Vercel AI SDK #Next.js AI chatbot #Gemma portfolio chat #llama.cpp tutorial
read post →Subscribe via RSS
/rss.xmlNew posts hit your reader instantly — no email, no tracking.