Primary source@atomic_chat_hq
View sourceEvent ·Multi-source
Atomic Local AI Server 发布:一个命令在本地跑各种推理引擎
Atomic 发布开源免费的 Local AI Server,支持 llama.cpp、vLLM、SGLang、TensorRT、MLX 等多种推理引擎,并根据 GPU、CPU 或 NPU 一键匹配安装。它提供 OpenAI 兼容 API,可从 Hugging Face 拉取 300 万个模型,支持 GGUF、MLX 和 safetensors 格式。运行环境覆盖 Windows、Linux、Apple Silicon 和 NVIDIA 硬件(含 RTX、Blackwell、DGX Spark)。还能连接 Hermes、OpenClaw、Claude、Codex 等智能体,并通过 stable-diffusion 生成图片和视频,提供 CLI、Web UI 和 Cloudflare 隧道远程访问。
Current read
想在本地跑开源模型又嫌装环境麻烦的可以试试这个,一条命令装好 llama.cpp 或 vLLM,还自带 OpenAI 兼容接口,能直接接 Claude 和 Codex 这类智能体。
11 sources43° AI heatLast updated 2026/11/4 17:53:37
Evidence
11 sourcesRelated source 1PyTorch
View sourceRelated source 2IT之家
View sourceRelated source 3shao__meng
View sourceRelated source 4NVIDIA AI
View sourceRelated source 5elvis
View sourceRelated source 6AIGCLINK
View sourceRelated source 7kimmonismus
View sourceRelated source 8Fireworks AI
View sourceRelated source 9宝玉
View sourceRelated source 10TestingCatalog
View sourceConflict check
Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.