Deploying the DeepSeek R1 distilled reasoning models on AMD Ryzen AI processors and Radeon graphics cards is easy and available now through LM Studio.
DeepSeek R1 Distilled Reasoning Models – AMD Ryzen AI and Radeon
DeepSeek R1 is a recently released ‘reasoning’ model that was distilled into highly capable smaller models. The new reasoning models are a new class of large language models (LLMs) designed to tackle highly complex tasks by using chain-of-thought (CoT) reasoning with the tradeoff of taking longer to respond.
Reasoning models add a ‘thinking’ stage before the final output which you can see by expanding the thinking window before it gives its final answer.
A reasoning model like the DeepSeek R1 Distilled Reasoning Model may first spend thousands of tokens to analyze the problem before giving a final answer. This allows it to be excellent at complex problem-solving tasks involving math and science and approach a problem from all angles before giving its response.
Depending on your AMD hardware, each of these models will offer state-of-the-art reasoning capability on your AMD Ryzen AI processor or Radeon graphics card.
Here’s how to do it:
- Make sure that you are on the 25.1.1 Optional or higher Adrenalin driver
- Download LM Studio 0.3.8 or above from the website
- Install LM Studio and skip the onboarding screen
- Click on the Discover tab
- Choose your DeepSeek R1 Distill. Smaller distills like the Qwen 1.5B offer fast performance while bigger distills will offer superior reasoning capability.
- On the right side, make sure the Q4 K M quantization is selected
- Click “Download”
- Once downloaded, head back to the chat tab
- Select DeepSeek R1 distill from the drop-down menu
- Make sure “manually select parameters” is checked
- In the GPU offload layers – move the slider all the way to the max
- Click model load
- Interact with a reasoning running model completely on your local AMD hardware
Here is a table of the maximum recommended DeepSeek R1 Distill size:
| Processor | DeepSeek R1 Distill* (Max Supported) |
|---|---|
| AMD Ryzen AI Max+ 395 32GB1, 64 GB2 and 128 GB | DeepSeek-R1-Distill-Llama-70B (64GB and 128GB only) DeepSeek-R1-Distill-Qwen-32B |
| AMD Ryzen AI HX 370 and 365 24GB and 32 GB | DeepSeek-R1-Distill-Qwen-14B |
| AMD Ryzen 8040 and Ryzen 7040 32 GB | DeepSeek-R1-Distill-Llama-14B |
*= AMD recommends running all distills in Q4 K M quantization.
1= Requires Variable Graphics Memory set to Custom: 24GB.
2= Requires Variable Graphics Memory set to High.
| Graphics Card | DeepSeek R1 Distill* (Max Supported1) |
|---|---|
| AMD Radeon RX 7900 XTX | DeepSeek-R1-Distill-Qwen-32B |
| AMD Radeon RX 7900 XT | DeepSeek-R1-Distill-Qwen-14B |
| AMD Radeon RX 7900 GRE | DeepSeek-R1-Distill-Qwen-14B |
| AMD Radeon RX 7800 XT | DeepSeek-R1-Distill-Qwen-14B |
| AMD Radeon RX 7700 XT | DeepSeek-R1-Distill-Qwen-14B |
| AMD Radeon RX 7600 XT | DeepSeek-R1-Distill-Qwen-14B |
| AMD Radeon RX 7600 | DeepSeek-R1-Distill-Llama-8B |
*= AMD recommends running all distills in Q4 K M quantization.
1= Lists the maximum supported distill without partial GPU offload.
Ram found his love and appreciation for writing in 2015 having started in the gaming and esports sphere for GG Network. He would then transition to focus more on the world of tech which has also began his journey into learning more about this world. That said though, he still has the mentality of "as long as it works" for his personal gadgets.
