Event ·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 sources
Primary source@atomic_chat_hq
View source
Related source 3shao__meng
View source
Related source 7kimmonismus
View source
Related source 8Fireworks AI
View source
Related source 10TestingCatalog
View source

Conflict 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.

Atomic Local AI Server runs local models via multiple engines · 事件专题 | AITOP