Ollama 推出云端模型预览，可运行 480B 等大模型
Cloud models · Ollama Blog
Ollama 上线云端模型预览，让用户在本地工具中运行个人电脑放不下的大模型，云端不保留用户数据。首批可用模型包括 qwen3-coder:480b-cloud、gpt-oss:120b-cloud、gpt-oss:20b-cloud 和 deepseek-v3.1:671b-cloud，需下载 Ollama v0.12 并登录 ollama.com。云端模型用法与普通模型一致，支持 ls、run、pull、cp，并可通过 Ollama 的 OpenAI 兼容 API 以及 JavaScript、Python、cURL 调用。
推荐理由
AI 评分 55
Ollama 把本地工具链延伸到云端大模型，读者可据此判断本地与云端混合推理的接入方式。
主题
正文
当前显示原文，中文全文译文尚未就绪。
September 19, 2025
Cloud models are now in preview, letting you run larger models with fast, datacenter-grade hardware. You can keep using your local tools while running larger models that wouldn’t fit on a personal computer. Ollama’s cloud does not retain your data to ensure privacy and security.
The same Ollama experience is now seamless across both local and in the cloud, integrating with the existing tools you already use. Ollama’s cloud models also work via Ollama’s OpenAI-compatible API.
Download Ollama v0.12, then open a terminal and run a cloud model:
Available models
qwen3-coder:480b-cloud; gpt-oss:120b-cloud; gpt-oss:20b-cloud; deepseek-v3.1:671b-cloud
Usage
Cloud models behave like regular models. For example, you can ls, run, pull, and cp them as needed:
Usage in Ollama’s API
JavaScript
First, install Ollama’s JavaScript library:
Next, pull a cloud model:
Once the model is available locally, run it using JavaScript:
Python
Download Ollama’s Python library
Next, pull a cloud model:
Once the model is available locally, run it using Python:
cURL
Pull a cloud model:
Next, call Ollama’s API to run the model
Signing in and out
Cloud models use inference compute on ollama.com and require being signed in to ollama.com:
To stay signed out, run:
Cloud API access
Cloud models can also be accessed directly via ollama.com’s API.