Skip to content

Ollama 0.30.7

Updated August 10, 2026 162 MB
Ollama 0.30.7

Download

0.30.7

File password: www.downloadly.ir

About this item

Descriptions

Ollama is an open-source framework and command-line tool designed to simplify the process of running, managing, and interacting with large language models (LLMs) locally on your own machine. By abstracting away complex setups and hardware configurations, Ollama allows users to easily download, run, and customize open-source models (such as Llama 3, Mistral, Gemma, and Qwen) entirely offline, providing a seamless, private, and highly efficient local AI experience.

Features of Ollama

  • Streamlined CLI: A powerful and intuitive command-line interface that allows users to effortlessly pull, run, list, and manage local models with simple commands (e.g., ollama run llama3).
  • Modelfile Customization: Offers a “Modelfile” system (similar to a Dockerfile) that lets users easily create custom versions of models by modifying system prompts, parameters, and templates.
  • Broad Model Library: Provides access to a comprehensive registry of popular open-source models, including Llama, Mistral, Phi, Gemma, and multimodal models like LLaVA.
  • Local REST API: Automatically spins up a local API server, allowing developers to easily integrate local LLMs into their own applications, scripts, or third-party UIs (like Open WebUI).
  • Hardware Acceleration: Optimized for high-performance local inference, featuring out-of-the-box support for Apple Silicon (Metal) GPUs, as well as NVIDIA (CUDA) and AMD (ROCm) graphics cards.
  • Cross-Platform Compatibility: Fully supports major operating systems, including macOS, Windows, and Linux, and can also be easily deployed via Docker.
  • Multimodal Capabilities: Supports multimodal models, enabling users to process and analyze images alongside text directly from the command line or via the API.
  • Context Window Management: Allows users to configure and adjust the context window size and other generation parameters (like temperature and top_p) on the fly.

System Requirements

Windows 10 22H2 or newer, Home or Pro

NVIDIA 452.39 or newer Drivers if you have an NVIDIA card

AMD ROCm v7 / HIP7-capable driver stack for ROCm acceleration, or a Vulkan-capable AMD Radeon driver for Vulkan acceleration

Pictures

Installation guide

It is free

Download Links

Ollama 0.30.7

Download Part 1 – 1 GB

Download Part 2 – 347 MB

Password file(s): www.downloadly.ir

File size

162 MB

What is included

  • Streamlined CLI:A powerful and intuitive command-line interface that allows users to effortlessly pull, run, list, and manage local models with simple commands (e.g.,ollama run llama3).
  • Modelfile Customization:Offers a “Modelfile” system (similar to a Dockerfile) that lets users easily create custom versions of models by modifying system prompts, parameters, and templates.
  • Broad Model Library:Provides access to a comprehensive registry of popular open-source models, including Llama, Mistral, Phi, Gemma, and multimodal models like LLaVA.
  • Local REST API:Automatically spins up a local API server, allowing developers to easily integrate local LLMs into their own applications, scripts, or third-party UIs (like Open WebUI).
  • Hardware Acceleration:Optimized for high-performance local inference, featuring out-of-the-box support for Apple Silicon (Metal) GPUs, as well as NVIDIA (CUDA) and AMD (ROCm) graphics cards.
  • Cross-Platform Compatibility:Fully supports major operating systems, including macOS, Windows, and Linux, and can also be easily deployed via Docker.
  • Multimodal Capabilities:Supports multimodal models, enabling users to process and analyze images alongside text directly from the command line or via the API.
  • Context Window Management:Allows users to configure and adjust the context window size and other generation parameters (like temperature and top_p) on the fly.

Requirements

  • Windows 10 22H2 or newer, Home or Pro
  • NVIDIA 452.39 or newer Drivers if you have an NVIDIA card
  • AMD ROCm v7 / HIP7-capable driver stack for ROCm acceleration, or a Vulkan-capable AMD Radeon driver for Vulkan acceleration

Screenshots

You might also want