Uploaded April 2026 | Updated November 2026, 10 hours ago
Are your local AI models running slowly on your CPU? In this tutorial, I show you how to force Ollama and your local LLMs to run 100% on your AMD GPU instead of the CPU. This simple environment variable fix will significantly speed up your business automations, like web scraping and content writing.
youtu.be/O9VvkG-wdPk
youtu.be/wDa3V7gtqOw
Subscribe here:
youtube.com/channel/UCP7I8JdA-r7Q9iH_apWv9Kg?sub_confirmation=1
Are your local AI models running slowly on your CPU? In this tutorial, I show you how to force Ollama and your local LLMs to run 100% on your AMD GPU instead of the CPU. This simple environment variable fix will significantly speed up your business automations, like web scraping and content writing.
youtu.be/O9VvkG-wdPk
youtu.be/wDa3V7gtqOw
Subscribe here:
youtube.com/channel/UCP7I8JdA-r7Q9iH_apWv9Kg?sub_confirmation=1










