README: model = AutoModel.from_pretrained("Qwen/Qwen3-32B")
GitHub 项目简介: AirLLM 70B inference with single 4GB GPU
README: AirLLM: scaling large language models on low-end commodity computers
README: The trick: AirLLM only ever keeps **one layer on the GPU at a time**, so the VRAM you need depends on the model's layer size — not its total size.