Tagged: Local

Articles

• From Scratch · Part 15Training LLMs

  Build an LLM From Scratch: From Our Model to Frontier Models

  Our 88M run next to Llama 3, DeepSeek-V3, OLMo 2 and SmolLM, the model exported to Hugging Face and llama.cpp, and the whole series reviewed.

• Inference · Part 13Inference & Optimization

  Running LLMs on Your Own Machine: llama.cpp, GGUF and Ollama

  How fast a model can run on your laptop and what fits: bandwidth math, unified memory, llama.cpp, GGUF quants, Ollama, MLX and measured numbers.