本地启动ollama大语言模型

官网

Ollama

安装

复制代码
root@master-node:~# snap install ollama

启动

复制代码
root@master-node:~# ollama run gemma:2b

输出

复制代码
verifying sha256 digest 
writing manifest 
removing any unused layers 
success 
>>> who are you?
I am a large language model, trained by Google. I am a conversational AI that can assist with a wide range of tasks, including language generation,
translation, question answering, and more.

Here are some key facts about me:

* I am a massive model, trained on a massive dataset of text and code.
* I am able to understand and generate human-like text in multiple languages.
* I am trained by Google, and I am not a human being.
* I am a conversational AI, which means I can have natural conversations with people.
* I am a powerful tool that can be used for a variety of purposes, such as education, entertainment, and business.

I am still under development, but I am constantly learning and growing. I am here to help you with your tasks and answer your questions to the best
of my ability.
相关推荐
m0_614523551 分钟前
普通视频怎么做多场景一镜到底:路线设计、逐段衔接与整体验收
人工智能·音视频
海宇服务18 分钟前
零信任架构实战:基于海宇对外投资历史查询服务构建自动化供应商准入网关
运维·人工智能·架构·自动化
东风破_28 分钟前
别急着上 Agentic RAG:先用 LangGraph 把最小 RAG 跑明白
人工智能
LaughingZhu1 小时前
Product Hunt 每日热榜 | 2026-09-12
人工智能·深度学习·神经网络·搜索引擎·百度
天真小巫1 小时前
2026.9.13总结(工作量日益繁重的当下,AI如何提效)
人工智能
Zguigo1 小时前
【CUDA1】GPUvsCPU,CUDA Kernel
人工智能·pytorch·深度学习
thesky1234561 小时前
用 ONNX Runtime 把 PyTorch 模型变成跨平台极速推理引擎:导出、优化、量化完整实
人工智能·深度学习·模型部署
米小虾1 小时前
把 KV Cache 从 3514 字节压到 890 字节:DeepSeek V4.1-Flash 动了什么,又没动什么
人工智能
锋行天下1 小时前
LangGraph 进阶:Command + Send 动态控制流、并行 Map-Reduce 实战与踩坑
人工智能
米小虾1 小时前
AI 观察:CEO 们集体喊"慢一点",钱却在加速进场
人工智能