Series
01Local StackA ground-up walk through a home LLM rig: what each part does, what it costs, and where you can cut corners without cutting quality.
› open series02QuantizationBits are not free. A practical tour of q4, q5, q8, and fp16 — what the numbers actually mean to your latency, your memory, and your output.
› open series03Inference Enginesllama.cpp, vLLM, and friends side by side. Same model, same machine, different results — measured, not marketed.
› open series04The Model ZooWhich open-weights models are worth the disk space right now, what they're good at, and what they hallucinate with confidence.
› open series05Hardware NotesReal numbers from real machines: memory bandwidth, thermal throttling, VRAM budgets. The spec sheet lies; the clock speed doesn't.
› open series06Running It DailyKeeping a local model honest over months, not minutes: updates, drift, tooling rot, and the mundane upkeep no blog post mentions.
› open series