Tag: llm

Self-host Gemma 4 or Qwen3-Coder via Ollama or llama.cpp in Docker, then let Claude delegate the grunt work to it. Free tokens, zero code leakage.

Stop burning expensive AI tokens on boring grunt work. The overseer/workhorse pattern routes mechanical tasks to a cheap model and saves more than you'd think.

Wire a self-hosted SearXNG instance into Claude Code via a Bash wrapper for private, scriptable web search, and when to use it vs the built-in tool.

Dify is an open-source LLM-app builder you can self-host. Visual workflow editor, RAG, agents, tool use, without writing 500 lines of LangChain glue.

OpenRouter is a hosted gateway, LiteLLM a self-hosted proxy, and Stripe now owns one of them. Which one belongs in your home lab as of August 2026?

Local LLMs can call tools, query APIs, and run code if you set them up right. Function calling on Ollama and llama.cpp explained, patterns that actually work.

Gemma 4 vs Qwen3.6: sizes, reasoning, coding benchmarks, and which model you should actually pull for your home lab rig.

AnythingLLM is the closest thing to a real private NotebookLM you can self-host. Workspaces, RAG, agents, document chat, running locally on Ollama in 20 minutes.

Pixtral, Qwen3-VL, and Gemma 4 compared for local multimodal use in 2026. LLaVA is dead; here's what to run in Ollama for OCR, screenshots, and vision tasks.

Model Context Protocol turns your LLM into a tool-using agent, file access, APIs, your home lab. Build your first MCP server in under 50 lines of Python.

Most RAG demos look great until you ship them. Ragas measures faithfulness, context precision, answer relevancy, the metrics that actually predict user trust.

How tiny 7B and 8B models keep punching above their weight, knowledge distillation, the teacher-student trick that makes local AI actually usable on home hardware.