Ollama Not Using GPU? How to Fix It on NVIDIA, AMD, Mac and Docker
Ollama not using GPU? Confirm with ollama ps, then check NVIDIA drivers, AMD ROCm, Vulkan, Mac and Docker, with the env vars and log paths to use.
Ollama not using GPU? Confirm with ollama ps, then check NVIDIA drivers, AMD ROCm, Vulkan, Mac and Docker, with the env vars and log paths to use.
Open WebUI Ollama setup with Docker or pip: create the admin account, connect to Ollama, download models and fix ‘can’t reach Ollama’ errors.
How to run Qwen locally: Ollama file sizes for Qwen3, 3.5, 3.6, 3.8, Coder and VL, a VRAM matching table, one-line commands and thinking-mode control.
What is a local LLM? See how local, offline and on-device models differ, how they compare with cloud AI on privacy, cost and capability, and who it suits.
Run DeepSeek locally the right way: R1 distills vs the full model vs V4, which Ollama tag fits 8GB to 48GB of VRAM, and four commands to get started.
想在自己电脑上本地部署大模型?按显存和内存讲清需要什么配置、8GB 到 48GB 能跑多大的模型,附 Ollama 上手五步和常见误区。
Ollama 安装教程:覆盖 Windows、macOS、Linux 的下载与安装,教你验证安装、跑通第一个模型、修改模型路径,并列出常见问题的排查顺序。
Ollama 不使用 GPU 怎么办?先用 ollama ps 确认,再按 NVIDIA 驱动、AMD ROCm、Vulkan、Mac、Docker 逐项排查,附环境变量与日志位置。
Open WebUI 安装教程:用 Docker 或 pip 部署,连接本机 Ollama,创建管理员、下载模型,并解决连接不上 Ollama 的常见问题。
Qwen 本地部署怎么做?Qwen3、3.5、3.6、3.8、Coder、VL 的 Ollama 文件大小、显存对应表、一键命令、思考模式开关与常见问题。