AI Tools
How AirLLM runs 70 billion parameter models on GPUs with a few gigabytes of memory
The open-source AirLLM library loads a model one layer at a time so that very large open models can run on consumer graphics cards, at the cost of speed.
Tag: local LLM
AI News
Tiiny AI shows Pocket Lab at CES 2026, a pocket-size PC that runs 120B parameter models offline
The Guinness-certified smallest mini PC packs 80GB of memory and 1TB of storage, runs large language models locally and heads to Kickstarter in February from $1,399.