Windows WSL2 Docker 本地大模型部署：在容器里用 NVIDIA 显卡跑 Ollama
Windows WSL2 Docker 本地大模型部署：装 WSL 2、共用 NVIDIA 驱动、用 –gpus 在 Docker 跑 Ollama、设内存上限，并对比原生版。
-
-
Dify and RAGFlow Local Deployment: Build a Private Knowledge Base App With Docker and Ollama
Dify and RAGFlow local deployment: requirements, Docker Compose steps, connecting Ollama, embedding models, and how to choose.
-
LLM Out of Memory Fix: A Local OOM Troubleshooting Checklist (Ollama and llama.cpp)
LLM out of memory fix for local models: check usage first, then cut context and parallelism, quantize the KV cache, and only then change model or hardware.
-
显存不足怎么办：本地大模型 OOM 排查清单（Ollama 与 llama.cpp）
本地大模型显存不足怎么办？按顺序排查：先查占用，再降上下文和并发，换 KV 缓存与量化，最后才加硬件，附 Ollama 与 llama.cpp 的具体设置。
-
Dify 和 RAGFlow 本地部署指南：用 Docker 和 Ollama 搭建团队私有知识库应用
Dify 和 RAGFlow 本地部署指南：硬件要求、Docker Compose 步骤、对接 Ollama、嵌入模型怎么选，以及两个平台如何取舍。
-
AnythingLLM 教程：用 Ollama 在自己电脑上和文档聊天
AnythingLLM 教程：安装桌面版或 Docker 版，连接 Ollama，选择嵌入模型，建立工作区，调好 Query 模式，并解决“找不到相关信息”的问题。
-
Build a Local Knowledge Base (RAG) with Ollama and Open WebUI or AnythingLLM
Local knowledge base setup with RAG: pair Ollama with Open WebUI or AnythingLLM, pick an embedding model, size chunks and context, and keep data private.
-
Ollama Download Slow? Change the Model Path and Speed It Up (2026)
Ollama download slow? Check proxies and resume, move models with OLLAMA_MODELS, and pull GGUF files from ModelScope or Hugging Face. Windows, Mac, Linux.
-
Gemma Local Deployment Guide: Run Gemma 4 and Gemma 3 with Ollama, Sized by VRAM
Gemma local deployment with Ollama: compare Gemma 4 e2b, e4b, 12b, 26b and 31b sizes and context, pick one by VRAM, and set thinking mode, sampling, and fixes.
-
gpt-oss Local Deployment Guide: Run gpt-oss-20b and gpt-oss-120b with Ollama and llama.cpp
gpt-oss local deployment with Ollama and llama.cpp: official memory needs for 20b and 120b, MXFP4, MoE offload flags, and reasoning effort.
