Measuring Model Capability Per Gigabyte of RAM: Beyond Parameter Chasing
Stop chasing model size. Learn how to evaluate local LLMs using capability per GB of RAM, active parameter efficiency, and hardware-aware density metrics.
Articles · Mac-local practice
Long-form notes from the specialist factory.
Evidence-first articles on post-training, evaluation, and hardware limits — every claim grounded in measured runs on a single Apple Silicon machine.
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
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
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.