Blog

Comparisons

Side-by-side looks at open-source tools that solve the same problem, so you can pick one and move on.

1 post
1 postRSS
Course

Local LLMs with Ollama & llama.cpp

Run open-weight LLMs on your own machine with Ollama and llama.cpp: GGUF, quantization, APIs, RAG, tool calling, tuning and security.

  • 01What Local LLMs Are and Why They Matter
  • 02The Mental Model: Tokens, Weights and Inference
  • 03Hardware Basics: RAM, VRAM and Bandwidth
30 lessonsView course