> Canonical page: https://posttrainllm.com/articles

Articles · Mac-local practice

# Long-form notes from the specialist factory.

Interactive explanations and evidence-first articles on model development, post-training, evaluation, and hardware limits. Teaching illustrations and measured local runs are clearly distinguished.

## [How to cook an LLM](https://posttrainllm.com/articles/how-to-cook-an-llm)

A garden-to-table journey through model-building: gather your data, inspect tokens, clean the batch, cook, refine, and serve.

## [Measuring Model Capability Per Gigabyte of RAM: Beyond Parameter Chasing](https://posttrainllm.com/articles/capability-per-gigabyte-ram-small-llms)

Stop chasing model size. Learn how to evaluate local LLMs using capability per GB of RAM, active parameter efficiency, and hardware-aware density metrics.

## [How to compare two fine-tuning runs without moving the evaluation target](https://posttrainllm.com/articles/how-to-compare-two-fine-tuning-runs-without-moving-the-evaluation-target)

Learn how to compare LLM fine-tuning runs effectively by freezing baselines, using frontier-calibrated gates, and measuring both primary and regression scores.

## [A Practical LoRA Evaluation Workflow for Mac-Local Models](https://posttrainllm.com/articles/lora-evaluation-workflow-mac-local-models)

Learn how to evaluate Mac-local LoRA adapters using frozen baselines, frontier calibration, AST matching, regression gates, and automated report cards.

## [How to Post-Train a Small Language Model on Apple Silicon](https://posttrainllm.com/articles/post-train-small-language-model-apple-silicon)

Learn how to post-train 0.6B–4B language models locally on Apple Silicon using LoRA, MPS, and MLX. Includes real run data, factory loops, and hardware constraints.