Details of AMD's upcoming Radeon RX 8000 "RDNA 4" GPU have been uncovered on Geekbench, shedding light on some of its key specifications. These early benchmark sightings suggest that AMD is currently conducting internal testing of the new GPUs in preparation for an anticipated launch next year. The leaked GPU, known as "GFX1201", is believed to be the Navi 48 SKU - the larger of the two dies planned for the RDNA 4 family.
According to the Geekbench listing, the GPU features 28 Compute Units, which in this context refers to Work Group Processors (WGPs). This places it between the current RX 7700 XT (54 CU) and RX 7800 XT (60 CU) models. The clock speed is reported to be 2.1 GHz, which may seem low compared to current RDNA 3 GPUs that can boost to 2.5-2.6 GHz. However, this is likely due to the early stage of the samples, and it is expected that higher frequencies will be achieved closer to the launch date. Memory specifications indicate 16 GB of VRAM, matching current high-end models and suggesting a 256-bit bus interface. Some versions may come with 12 GB VRAM and a 192-bit bus. While not officially confirmed, previous reports suggest that AMD will utilize GDDR6 memory. Performance in the OpenCL benchmark is currently underwhelming, but this is common for early engineering samples and should not be a cause for concern.
The RDNA 4 GPUs are anticipated to introduce new ray tracing engines with significant performance enhancements. AMD's goal is to deliver high-end performance within the $400-$500 price range with this new generation. More details are expected to be unveiled at the upcoming CES event.
