Skip to content

How-ToGPU

How to Update Ollama on Windows: Automatic and Manual Updates

Ollama on Windows downloads updates automatically: click its taskbar icon and choose Restart to update, or download and run the latest installer, which doesn't need Administrator rights. Updating keeps your models, upgrade.log in %LOCALAPPDATA%\Ollama helps if it fails, and Ollama lists minimum GPU drivers.

By , Editorial team

1 min read

How to Update Ollama on Windows: Automatic and Manual Updates

If a newly released model won't download or load in Ollama, an out-of-date install is one of the first things to check. Ollama's documentation says the company updates it regularly to support the latest models. Here's how to keep it current on Windows, based on Ollama's official docs; Forge PC hasn't tested every version.

Method 1: apply the automatic update

Ollama's FAQ says Ollama on Windows automatically downloads updates. To apply one:

  1. Click the Ollama icon in the taskbar notification area.

  2. Click Restart to update.

Ollama then restarts on the new version.

Method 2: update manually

The FAQ also says you can install updates by downloading the latest version manually. Download the Windows installer from Ollama's site and run it. Ollama's Windows docs say the installer doesn't require Administrator rights and installs in your account.

Updating doesn't delete your downloaded models. They stay in your models folder (by default C:\Users\<your name>\.ollama\models, or wherever you've pointed it; see our guide to moving Ollama models to another drive, also in this batch).

If something goes wrong

Ollama's Windows docs list useful folders for troubleshooting:

  • %LOCALAPPDATA%\Ollama contains logs and downloaded updates; upgrade.log contains log output for upgrades.

  • %LOCALAPPDATA%\Programs\Ollama contains the program files.

Type explorer %LOCALAPPDATA%\Ollama into the Run box (Windows + R) to open the logs folder.

Don't forget your GPU driver

Ollama's hardware support page lists minimum drivers, for example NVIDIA driver 550 or newer (570 or newer for older compute capability 5.0-6.2 cards). If GPU acceleration isn't working, see how to update graphics drivers, and for model management afterwards, how to manage Ollama models.

Our verdict

On Windows, Ollama downloads updates itself: click its taskbar icon and choose Restart to update, or download and run the latest installer. Your models are kept, and the upgrade.log file in %LOCALAPPDATA%\Ollama helps if an update fails.

The bottom line

On Windows, Ollama downloads updates itself: click its taskbar icon and choose Restart to update, or download and run the latest installer. Your models are kept, and the upgrade.log file in %LOCALAPPDATA%\Ollama helps if an update fails.

Sources

  1. 01Ollama, FAQ (How can I upgrade Ollama?)
  2. 02Ollama, Windows documentation
  3. 03Ollama, Hardware support

About the author

Forge PC Staff

Editorial team

The shared byline for articles researched, written and edited by the Forge PC editorial team. How we source, check and correct our work is set out in our editorial policy.

More from Forge PC Staff

Read next

How to Check Your Wi-Fi Signal Strength in Windows 11

How-To

How to Check Your Wi-Fi Signal Strength in Windows 11

Check Wi-Fi signal strength in Windows 11 from the taskbar bars, Settings > Network & internet, or exactly with netsh wlan show interfaces (the Signal percentage). Windows Central treats 80-100% as reliable and below 60% as weak. netsh wlan show wlanreport summarises recent wireless sessions.

Forge PC Staff2 min

How to Turn Thinking On or Off in Ollama (DeepSeek-R1, Qwen 3, gpt-oss)

How-To

How to Turn Thinking On or Off in Ollama (DeepSeek-R1, Qwen 3, gpt-oss)

Ollama lets you control reasoning models' thinking: --think and --think=false on the command line, /set think and /set nothink in chats, --hidethinking for scripts and a think field in the API. Check /api/show first, as models such as gpt-oss use low, medium and high levels instead.

Forge PC Staff2 min

How to Use Embedding Models in Ollama for Local Semantic Search and RAG

How-To

How to Use Embedding Models in Ollama for Local Semantic Search and RAG

Embedding models turn text into vectors for semantic search and RAG. Pull one such as embeddinggemma in Ollama, generate vectors with ollama run or the /api/embed endpoint, store them, then embed questions with the same model and compare using cosine similarity, all locally.

Forge PC Staff3 min

How to Fix Windows Search Not Working in Windows 11

How-To

How to Fix Windows Search Not Working in Windows 11

If Windows 11 search stops finding files or apps, follow Microsoft's fixes in order: end SearchHost.exe in Task Manager, install updates, run the Search and Indexing troubleshooter, check Classic or Enhanced indexed locations, then rebuild the index and allow up to 24 hours.

Forge PC Staff3 min