Our AI strategy at AMD is focused on enabling the ecosystem with a broad portfolio of training and inference compute engines, open and proven software capabilities, and nurturing the AI ecosystem through co-innovation. We continue to be focused on enabling the next generation of AI models for everyone and make the benefits of AI pervasive.
We are encouraged by the recent release of the Llama 3 model from Meta. Llama 3 is the most capable open source model available from Meta to-date with strong results on HumanEval, GPQA, GSM-8K, MATH and MMLU benchmarks. It comes in 8 billion and 70 billion parameter flavors where the former is ideal for client use cases, the latter for more datacenter and cloud use cases.
Good news. AMD customers with a Ryzen™ AI1 based AI PC or AMD Radeon™ 7000 series graphics cards2 can experience Llama 3 completely locally right now – with no coding skills required.
AMD Ryzen™ Mobile 7040 Series and AMD Ryzen™ Mobile 8040 Series processors feature a Neural Processing Unit (NPU) which is explicitly designed to handle emerging AI workloads. Featuring up to 16 TOPs, the NPU allows the user to execute AI workloads with maximum power efficiency. AMD Ryzen™ AI APUs also include the CPU and iGPU – which are used to handle on-demand tasks. Check out this video to learn more about AMD Ryzen™ AI PCs.
In this blog, we will demonstrate how to quickly and easily run Meta’s Llama 3 Instruct 8 billion parameter model on your AMD hardware.
1. Download the correct version of LM Studio:
|
For AMD Ryzen Processors |
For AMD Radeon RX 7000 Series Graphic Cards |
2. Run the file.
3. Click the “Download” button on the Llama 3 – 8B Instruct card.
4. Once downloaded, click the chat icon on the left side of the screen.
5. Select Llama 3 from the drop down list in the top center.
6. Select “Accept New System Prompt” when prompted.
7. If you are using an AMD Ryzen™ AI based AI PC, start chatting!
For users with AMD Radeon™ 7000 series graphics cards, there are just a couple of additional steps:
8. Click on "Advanced Configuration" on the right hand side.
9. Scroll down until you see "Hardware Settings". Make sure “GPU Offload” is selected and the slider is all the way to the right (Max). Click on “Reload model to apply configuration” if prompted.
10. Start chatting with Meta’s new Llama 3 chatbot.
It’s as simple as that.
AMD is committed to advancing AI, making the benefits of AI pervasive. AI PCs from AMD enable everyone to benefit from the growth in AI consumer applications. Click here to learn more about AMD Ryzen AI.
Footnotes:
1. Ryzen™ AI is defined as the combination of a dedicated AI engine, AMD Radeon™ graphics engine, and Ryzen processor cores that enable AI capabilities. OEM and ISV enablement is required, and certain AI features may not yet be optimized for Ryzen AI processors. Ryzen AI is compatible with: (a) AMD Ryzen 7040 and 8040 Series processors except Ryzen 5 7540U, Ryzen 5 8540U, Ryzen 3 7440U, and Ryzen 3 8440U processors; and (b) all AMD Ryzen 8000G Series desktop processors except the Ryzen 5 8500G/GE and Ryzen 3 8300G/GE. Please check with your system manufacturer for feature availability prior to purchase. GD-220b.
2. Radeon™ RX 6000 and RX 7000 Series graphics cards (and later models) are not designed, marketed nor recommended for datacenter usage. Use in a datacenter setting may adversely affect manageability, efficiency, reliability, and/or performance. GD-240.
Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied. GD-97.