下载Ollama官方镜像 Windows 安装版本
Ollama是一个开源的、简明易用的本地大模型运行框架,旨在简化大型语言模型(LLM)的部署和运行过程。其主要特点和功能包括:12
1、完成后双击OllamaSetup.exe文件,出现如下弹窗,点击 Install
等待下载完成即可。
2、安装完成之后,打开一个cmd命令窗口,输入“ollama”命令,如果显示ollama相关的信息就证明安装已经成功了!
ollama run qwen2.5:3b
也可以选择其它模型库:
The current strongest model that fits on a single GPU.
180.6K Pulls 13 Tags 888.2K Pulls 8 Tags 25.9M Pulls 29 Tags 1.5M Pulls 14 Tags 1M Pulls 5 Tags 10.5M Pulls 63 Tags 26.8M Pulls 93 Tags 18.9M Pulls 3 Tags 10.2M Pulls 84 Tags 7.6M Pulls 68 Tags 5.3M Pulls 133 Tags 4.6M Pulls 196 Tags 4.5M Pulls 379 Tags 4.4M Pulls 102 Tags 4.1M Pulls 97 Tags 4M Pulls 98 Tags 3.4M Pulls 94 Tags 3.1M Pulls 102 Tags Updated 14 months ago
Updated 2 hours ago
QwQ is the reasoning model of the Qwen series.
Updated 7 days ago
DeepSeek's first-generation of reasoning models with comparable performance to OpenAI-o1, including six dense models distilled from DeepSeek-R1 based on Llama and Qwen.
Updated 4 weeks ago
New state of the art 70B model. Llama 3.3 70B offers similar performance compared to the Llama 3.1 405B model.
Updated 3 months ago
Phi-4 is a 14B parameter, state-of-the-art open model from Microsoft.
Updated 2 months ago
Meta's Llama 3.2 goes small with 1B and 3B models.
Updated 5 months ago
Llama 3.1 is a new state-of-the-art model from Meta available in 8B, 70B and 405B parameter sizes.
Updated 3 months ago
A high-performing open embedding model with a large token context window.
Updated 12 months ago
The 7B model released by Mistral AI, updated to version 0.3.
Updated 7 months ago
Meta Llama 3: The most capable openly available LLM to date
Updated 9 months ago
Qwen2.5 models are pretrained on Alibaba's latest large-scale dataset, encompassing up to 18 trillion tokens. The model supports up to 128K tokens and has multilingual support.
Updated 5 months ago
The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing.
Updated 4 months ago
Qwen 1.5 is a series of large language models by Alibaba Cloud spanning from 0.5B to 110B parameters
Updated 10 months ago
Gemma is a family of lightweight, state-of-the-art open models built by Google DeepMind. Updated to version 1.1
Updated 11 months ago
Qwen2 is a new series of large language models from Alibaba group
Updated 6 months ago
🌋 LLaVA is a novel end-to-end trained large multimodal model that combines a vision encoder and Vicuna for general-purpose visual and language understanding. Updated to version 1.6.
Updated 13 months ago
Google Gemma 2 is a high-performing and efficient model available in three sizes: 2B, 9B, and 27B.
Updated 7 months ago
Llama 2 is a collection of foundation language models ranging from 7B to 70B parameters.
学习实践小窍门
理论 + 实践、动脑 + 动手进步更快,云服务器可以帮助学习和实践。
可以搭建学习平台、搭建自己的Web服务/网站/博客、搭建网盘、安装各种软件和系统……
推荐腾讯云和阿里云:
[腾讯云] 新客户无门槛 | 送2860元代金券! 十周年感恩活动,云服务器首年95元!
[阿里云] 爆款特惠,低至不到1折! 多种优惠券 | 学生特惠专享!
有个入门级云服务器完全够用了,你就可以随时随地做开发和学习了。
本文系作者在时代Java发表,未经许可,不得转载。
如有侵权,请联系nowjava@qq.com删除。