
官网
https://ollama.com/
开源地址
https://github.com/ollama/ollama
特点
启动并运行大型语言模型。 运行 Llama 3、Phi 3、Mistral、Gemma 和其他模型。自定义并创建自己的。
支持本地知识库
使用说明下载安装ollama
下载地址:https://ollama.com/download
用ollama下载模型
例如:
ollama pull llama3开始使用
例如:
ollama run llama3
搭配

您应该至少有8 GB的RAM用于运行7B模型,16 GB用于运行13B模型,32 GB用于运行33B模型。
普通的家用电脑上也可以运行本地大模型了。
搭配网页或桌面客户端,可以想访问“豆包”、“chatgpt”一样使用自己电脑上的大模型。

Open WebUIEnchanted (macOS native)HollamaLollms-WebuiLibreChatBionic GPTHTML UISaddleChatbot UIChatbot UI v2Typescript UIMinimalistic React UI for Ollama ModelsOllamacbig-AGICheshire Cat assistant frameworkAmicachatdOllama-SwiftUIDify.AIMindMacNextJS Web Interface for OllamaMstyChatboxWinForm Ollama CopilotNextChat with Get Started DocAlpaca WebUIOllamaGUIOpenAOEOdin RunesLLM-X (Progressive Web App)AnythingLLM (Docker + MacOs/Windows/Linux native app)Ollama Basic Chat: Uses HyperDiv Reactive UIOllama-chats RPGQA-Pilot (Chat with Code Repository)ChatOllama (Open Source Chatbot based on Ollama with Knowledge Bases)CRAG Ollama Chat (Simple Web Search with Corrective RAG)RAGFlow (Open-source Retrieval-Augmented Generation engine based on deep document understanding)StreamDeploy (LLM Application Scaffold)chat (chat web app for teams)Lobe Chat with Integrating DocOllama RAG Chatbot (Local Chat with multiple PDFs using Ollama and RAG)BrainSoup (Flexible native client with RAG & multi-agent automation)macai (macOS client for Ollama, ChatGPT, and other compatible API back-ends)
Open WebUI的界面