Distribute and run LLMs with a single file. Contribute to mozilla-ai/llamafile development by creating an account on GitHub.

And it seems to work well, too. Download an LLM and application all in one file. Slick.

Anthropic's latest interpretability research: a new microscope to understand Claude's internal mechanisms

Selected text

Language models like Claude aren't programmed directly by humans—instead, they‘re trained on large amounts of data. During that training process, they learn their own strategies to solve problems. These strategies are encoded in the billions of computations a model performs for every word it writes. They arrive inscrutable to us, the model’s developers. This means that we don’t understand how models do most of the things they do.

THIS looks interesting. Run gigantic LLMs locally, on something the size of a Mac mini (well, mini+).

Work with AI models locally with up to 200 billion parameters. 128GB of unified system memory. Preloaded with the NVIDIA AI software stack. On your desktop.

Selected text: Powered by the NVIDIA GB10 Grace Blackwell Superchip, NVIDIA DGX™ Spark delivers one petaFLOP1 of AI performance in a power-efficient, compact form factor. With the NVIDIA AI software stack preinstalled and 128 GB of memory, developers can prototype, fine-tune, and inference the latest generation of reasoning AI models from DeepSeek, Meta, NVIDIA, Google, Qwen and others with up to 200 billion parameters locally.