How to Enable Ollama GPU Acceleration on Intel Arc in Windows

Posted by on


I recently encountered an interesting performance issue while running Ollama locally on my ASUS ZenBook with an Intel Arc 140T integrated GPU.

I was sure that I had enough GPU:


However, every model I tested was extremely slow, including relatively small models such as Qwen3 4B.

After investigating, I discovered that Ollama was running entirely on the CPU instead of using the GPU.

Identifying the problem

Ollama provides a simple command to check where a model is running:

ollama ps

Initially, the output showed:

NAME       SIZE     PROCESSOR   CONTEXT
qwen3:4b   3.9 GB   100% CPU    8192

The GPU was not being used.

Enabling Intel Arc GPU acceleration

The solution was to enable two environment variables:

$env:OLLAMA_VULKAN = "1"
$env:OLLAMA_IGPU_ENABLE = "1"

The first enables Ollama's experimental Vulkan backend, while the second allows integrated GPU detection.

After completely closing Ollama, I restarted the server:

ollama serve

Then I loaded the model again:

ollama run qwen3:4b

Checking the processor allocation:

ollama ps

This time, the result was:

NAME       SIZE     PROCESSOR   CONTEXT
qwen3:4b   3.2 GB   100% GPU    4096

Success! Ollama is now using the Intel Arc GPU.

Making the configuration permanent

To avoid setting the variables every time Ollama starts, configure them permanently in PowerShell:

[Environment]::SetEnvironmentVariable("OLLAMA_VULKAN", "1", "User")
[Environment]::SetEnvironmentVariable("OLLAMA_IGPU_ENABLE", "1", "User")

Restart Ollama after applying these changes.

Final thoughts

This experiment was performed using:
  • GPU: Intel Arc 140T
  • Driver: 32.0.101.8860
  • OS: Windows 11 26H2
  • Ollama: 0.40.11
  • Model: Qwen3 4B
The interesting lesson is that **having a GPU capable of running a model does not guarantee that your inference engine is actually using it**.

Tools that estimate whether a model fits into memory are useful, but actual hardware utilization matters just as much.

I believe Ollama could improve the user experience by displaying GPU utilization directly in its interface and warning users when a compatible GPU is available, but inference is running on the CPU.

Until then, ollama ps is your friend!

Notes:
  • Vulkan acceleration remains experimental, and results may vary depending on your Intel GPU, drivers, and Ollama version.
  • I created this ticket on GitHub; maybe they could support it from the UI in the future.

Comments

Post a Comment