Explore all 26 articles about Local LLMs. Practical guides, reviews, and deep dives — tested and published regularly.
All 26 articles in this topic, newest first.
Running Ollama in Docker with GPU passthrough, persistent storage, and reverse proxy. Full annotated compose file and environment setup from my actual homelab.
·
·
7 min read
Jan local LLM client crashes on startup or won't load models. Here's what I tried, what…
LocalAI won't start? Model loads fail? I ran into five concrete errors setting up LocalAI locally.…
Tested three ways to run a ChatGPT-like interface on your own hardware. Open WebUI vs Ollama…
Comparing Ollama against LM Studio and Text Generation WebUI for running open-source LLMs locally. Which tool…
Step-by-step guide to installing GPT4All on Ubuntu for a private, offline chatbot. No GPU required, runs…
Jan's API server can talk to Home Assistant. Here's how to wire them together, what works,…
LM Studio architecture explained: how model discovery, downloading, quantization, and inference actually work when you run…
I switched from Ollama to Text Generation WebUI today. Here's what I gained, what I'm missing,…
I set up LocalAI to replace cloud LLM calls in my automations. Took about an hour,…
