Ollama Windows Preview Release

Ollama is now available on Windows in preview, allowing users to to pull, run, and create large language models (LLMs) through a native Windows experience. This release enables local model execution with built-in GPU acceleration and full access to the Ollama model library and API.

Native Hardware Acceleration

Ollama on Windows provides hardware acceleration to optimize model performance without requiring virtualization or manual configuration. The software accelerates model execution using NVIDIA GPUs and modern CPU instruction sets, specifically AVX and AVX2, when available.

Model Library and Vision Capabilities

Windows users have full access to the Ollama model library, including vision models. For vision-capable models such as LLaVA 1.6, users can add images to messages by dragging and dropping them directly into the ollama run command.

Background API and OpenAI Compatibility

Ollama's API runs automatically in the background on http://localhost:11434, allowing external tools and applications to connect without additional setup.

Key API features include:

  • OpenAI Compatibility: The Windows preview supports the same OpenAI compatibility as other Ollama platforms, enabling the use of existing OpenAI-based tooling with local models.
  • PowerShell Integration: The API can be invoked directly via PowerShell using Invoke-WebRequest to send POST requests to the local endpoint.

Installation and Setup

To begin using the Windows Preview, users can download the OllamaSetup.exe installer. After installation, models can be executed via the terminal using the command ollama run llama2. The application will prompt users for updates as new releases are made available.

Sources

Related

  • Dispatch
    Ollama Cloud Models Preview

    Ollama has introduced Cloud models in preview, enabling users to run large-scale models on datacenter-grade hardware while maintaining the same local toolset and API integration.

  • Dispatch
    Ollama App Release for macOS and Windows

    Ollama has released a new application for macOS and Windows that provides a graphical user interface for downloading and chatting with local AI models, including support for file uploads and multimodal capabilities.

  • Dispatch
    Ollama Tool Support Release

    Ollama has introduced tool calling support for models like Llama 3.1, allowing local LLMs to interact with external APIs, functions, and code interpreters.

  • Dispatch
    Ollama Official Docker Image Release

    Ollama has released an official Docker sponsored open-source image to simplify the deployment of large language models locally.

  • Project
    ollama/ollama

    Ollama is a cross‑platform runtime that lets you download and run open‑source large language models locally. It offers a CLI, a REST API (localhost:11434), and official Python/JS SDKs, plus many community integrations (web UIs, LangChain, AutoGPT, etc.). Install with a one‑line script or Docker, then launch models like `ollama run gemma4` or use `ollama launch` to connect to coding assistants or personal bots.