{"type": "article", "title": "AirLLM: Inference 2.8T Kimi K3 on a single 4GB GPU", "publisher": "Web Pulse", "url": "https://wpnews.pro/news/airllm-inference-2-8t-kimi-k3-on-a-single-4gb-gpu", "original_source": "https://github.com/lyogavin/airllm", "published": "2026-08-02T09:02:00+00:00", "accessed": "2026-08-02", "id": "airllm-inference-2-8t-kimi-k3-on-a-single-4gb-gpu"}