With the release of OpenAI's GPT-OSS 20B & 120B AI models, AMD is announcing that its Ryzen AI MAX & Radeon GPUs fully support them with enhanced capabilities.
AMD's Ryzen AI MAX+ 395 APU Is The Only AI Chip Capable of Running OpenAI's GPT-OSS 120B AI Model Natively, Radeon GPU Support is Also Announced
Yesterday, OpenAI released two brand new AI models, the GPT-OSS 20B & GPT-OSS 120B, the open-weight successors to GPT-2 from 2019. AMD has announced that its Ryzen AI CPUs and Radeon GPUs offer Day-0 support for these models and are available to try out via LM Studio.
So what is GPT-OSS?, These are open-weight models that are designed to handle complex reasoning and agentic capabilities. While most AI PCs and AI chips will be able to handle the 20B model, the 120B model requires more hardware resources. This is where AMD's Strix Halo or Ryzen AI MAX chips come in. With a maximum memory pool of 128 GB, these chips are designed to natively handle such AI models.
The GGML converted MXFP4weights require roughly 61GB of VRAM and fit effortlessly into the 96GB dedicated graphics memory of the AMD Ryzen AI Max+ 395 processor. Note that a driver version equal to or higher than AMD Software: Adrenalin Edition 25.8.1 WHQL is required to unlock this capability.
With speeds of up to 30 tokens per second, not only do AMD customers have access to a datacenter-class, state-of-the-art model, but the performance is very usable thanks to the bandwidth of the Ryzen AI Max+ platform and the mixture-of-experts architecture of the OpenAI GPT-OSS 120B. Because of its large memory, the Ryzen AI Max+ 395 (128GB) also supports Model Context Protocol (MCP) implementations with this model. Users with AMD Ryzen AI 300 series processors can also take full advantage of the smaller 20B model from OpenAI.
For lightning-fast performance with the OpenAI GPT-OSS 20B model, users can use the AMD Radeon 9070 XT 16GB graphics card in a desktop system. Not only does this setup offer lightning-fast tokens per second, but it also has an incredible TTFT advantage. This means that users utilizing Model Context Protocol (MCP) implementations with the 20B models will find extremely responsive TTFT performance with this setup in typically compute-bound situations.
Experience OpenAI's GPT-OSS 120B and 20B models on AMD Ryzen AI processors and Radeon graphics cards
- Download and install AMD Software: Adrenalin Edition 25.8.1 WHQL drivers or higher. Please note that performance and support may be degraded or absent in older drivers.
- If you are on an AMD Ryzen AI-powered machine, right-click on Desktop > AMD Software: Adrenalin Edition > Performance Tab > Tuning Tab> Variable Graphics Memory > please set VGM according to the specification table given below. If you are on an AMD Radeon graphics card, you can ignore this step and proceed.
- Download and install LM Studio.
- Skip onboarding.
- Go to the discover tab (magnifying glass)
- Search for “gpt-oss”. You should see an option with the "LM Studio community" prefix on the left-hand side. Please select either the 20B or the 120B variant (whichever corresponds to your product in the matrix given below). Click download.
- Go to the chat tab.
- Click on the drop-down menu at the top and select the OpenAI model. Make sure to click “Manually load parameters”
- Move the “GPU Offload” slider to the MAX. Check the remember settings.
- Click load. If you are using the 120B model, it may take a while, and the loading bar may seem like it is stuck (the read speeds of most SSDs fall off after a burst, and this is a large model to move to memory!).
- Start prompting!
AMD has also shared a product support list for OpenAI's GPT-OSS models. It's Ryzen AI MAX+ 395 is the only chip to handle the 120B model, while the rest, including its Radeon RX 9000, Radeon AI PRO R9000 & Radeon RX 7000 GPUs with at least 16 GB memory, can handle the GPT-OSS 20B models with relative ease.
Follow Wccftech on Google to get more of our news coverage in your feeds.
