4 docs tagged with "local-ai"

Testing vLLM and SGLang against Ollama on Tanker (Maxwell) and Galleon (Ampere) — and why matching the compute capability isn't enough.

The champion answered the question correctly — and then produced three paragraphs of unrelated text. This is not a failure of the model. It is a failure of the layer that was never built on top of it.

Benchmarking 12B models across the fleet — MLX, CPU, and Vulkan — and the ship role reassignment that followed.

Era II — M21, M23, M24, M25. The fleet cleaned its memory, automated its chronicle, gained conditional intelligence, and made trust a measurable thing.