“Up to 4.3x faster” AMD’s new Amuse 3.0 AI works on most Radeon GPUs, but it works best on the 9070 XT
Table of Contents
AMD, in collaboration with TensorStack AI, recently announced Amuse 3.0, the latest version of its AI-powered content creation platform designed to run entirely on personal computers with Ryzen AI processors and Radeon graphics cards. The platform supports over 100 AI models, including Stable Diffusion 3.5, FLUX, and many more, all optimized for AMD’s hardware architecture, and comes with a bunch of new features.
The key benefit of Amuse 3.0 is local data processing, which means there's no need to send information to external servers, reducing reliance on an internet connection and enhancing privacy. As a result, system requirements are what everyone is asking about. Turns out, you can technically run a few specific AI models on older AMD GPUs, but AMD’s latest hardware is where it shines best.
6GB AMD cards can run these two AI models
According to the system requirements provided by AMD, those with older AMD GPUs featuring at least 6GB of VRAM can run the SD 1.5 (Stable Diffusion 1.5) and LCM (Latent Consistency Models) AI models, meaning basic image generation and lightweight content creation tasks remain accessible even without the latest hardware.
| Models | AMD Radeon™ Graphics Cards | AMD Ryzen™ AI Processors |
|---|---|---|
| SD 1.5 and LCM | Most AMD Radeon™ Graphics Card with at least 6GB of vRAM | Most AMD laptops with 16GB RAM. |
| SDXL, SDXL Lightning, SD3 Medium, SD 3.5 Medium | AMD Radeon™ RX 9070 XT, Radeon 7900 XTX, Radeon 7900 XT, Radeon 7900 GRE, Radeon 7800 XT | AMD Ryzen™ AI 300 series with 32GB RAM, Ryzen AI™ 395+ MAX series with 32GB RAM. (VGM = 16GB) |
| FLUX.Schnell, SD 3.5 Large Turbo | AMD Radeon™ RX 9070 XT, Radeon 7900 XTX, Radeon 7900 XT, Radeon 7900 GRE, Radeon 7800 XT | AMD Ryzen™ AI MAX+ 395 series with 64GB or 128GB RAM. (VGM = 48GB) |
| SD 3.5 Large, FLUX.Dev | AMD Radeon™ PRO W7900 XT 48GB, Radeon™ PRO W7800 48GB | – |
However, if you're aiming to achieve the “up to 4.3x” inference speed AMD claims, you'll need the latest RX 9070 XT GPU. With these graphics cards, users can expect up to 4.3x faster image generation in Stable Diffusion 1.5, 3.1x faster performance in SDXL 1.0, and in the SD 3.5 family of models, up to 3.3x faster performance in SD 3.5 Large.
That said, AMD's last-gen flagship, the 7900 XT, is also no slouch and can handle nearly all AI models just as effectively as the 9070 XT, except for the SD 3.5 family. This means that even with consumer-level AMD GPUs, users can easily leverage AMD’s latest optimized AI models without having to worry about performance issues.
About the Author