Skip to content
Fantástico Mundo de Jon
RSS

All posts

  1. Coloring Pages with Local AI: From Prompt to a File That Prints Well

    Generating the image is the easy part, and that's where most tutorials end. What determines whether the child can paint is what comes next: binarizing, vectorizing, and printing without jagged edges.

  2. Qwen3.6 27B: How Much VRAM It Really Needs

    A 27B model that uses half the KV cache of a Llama 3 8B. The hybrid architecture breaks the usual calculation — and decides, for less than 1 GB, which cards are left out.

  3. How much VRAM an LLM really uses

    The back-of-the-envelope math — parameters times bits — is off by several gigabytes, because it ignores the KV cache. Here is the full calculation, with the formula, the numbers and how to verify it on your own GPU.

  4. I measured whether a spec file makes the model more accurate. It doesn't.

    In July I argued that structured spec changes the outcome. I measured in October: 360 generations, 3 local models, 3 ways of asking for the same thing. What pays off is the written information, not the file format.

  5. The PRD comes first: the spec that prevents the agent from writing incorrect code

    The model doesn't make mistakes due to ignorance: it makes mistakes because it filled the gap the prompt left, and filled it in a plausible way. What changes in the code when the contract comes before the request.