{"slug":"airllm","name":"airllm","category":"local-inference","categoryName":"Local inference & serving","audience":["for-ai","ai-era"],"primary":"ai-era","openClosed":"open","pricing":"open-source","license":"apache-2.0","maintained":"yes","officialUrl":"https://github.com/lyogavin/airllm","repo":"https://github.com/lyogavin/airllm","latestVersion":null,"latestRelease":null,"stars":40163,"starsAsOf":"2026-10-22","description":"Run 70B inference on a single 4GB GPU.","descriptionZh":"在 4GB 显存上推理 70B 模型。","callMethods":[],"platforms":["Python"],"addedAt":"2026-10-10","updatedAt":"2026-10-22","topics":[],"language":"Jupyter Notebook","lastPush":"2026-10-21","formerly":null,"packages":[],"recentVersions":[],"alternatives":["ollama","llama-cpp","vllm","cherry-studio","localai","exo","sglang","mlx"],"stacks":[],"scenarios":["switch-models","run-models-locally","use-ai-compliantly-in-china","learn-ai"],"problems":[],"reasonZh":null,"sources":["hot","github-pool"],"record":"https://aimap.page/api/v1/software/airllm.json","pages":{"en":"https://aimap.page/en/software/airllm/","zh-hans":"https://aimap.page/zh-hans/software/airllm/"}}