AMD Radeon Pro W6800 to be the first Navi 21 graphics card with 32GB memory

AMD Radeon Pro W6800 is an RX 6800 with more memory for workstations

According to the latest leak, the upcoming Radeon PRO W6800 graphic card will feature 30 Compute Units, just as many as the gaming Radeon RX 6800 model.

The graphics card has just appeared on Geekbench, where it was tested in the OpenCL benchmark. According to the benchmark, this SKU would feature 30 Compute Units (for AMD RDNA2 GFX1030 architecture this means 60 Compute Units), which means it will have 3840 Stream Processors, just as many as Radeon RX 6800 for gaming. A major change comes to the memory configuration though. AMD has added 32GB of memory to the graphics card, which is twice as much as Radeon RX 6800/6900 series.

AMD Radeon Pro W6800 32GB, Source: Geekbench

The graphics card relatively high maximum core clock of 2554 MHz. However, we do not know how accurate this reading is and for how long can such a frequency can be sustained. The workstation graphics cards are also further restricted by their TDP and thermal characteristics, which is especially important on blower-type cooling designs. It is more or less confirmed that the PRO W6800 will feature such a cooler.

The graphics card scored 137230 points in the OpenCL test, which is actually higher than Radeon RX 6800 according to official charts.

AMD Radeon Pro W6800 32GB, Source: Geekbench

AMD confirmed it will have a special announcement on June 8th . The company has inadvertently confirmed that the event will feature Radeon Pro W6800 and W6600 workstation graphics card.s

AMD Radeon PRO W6800 Geekbench Performance
VideoCardzOpenCLCUDA
NVIDIA GeForce RTX 3090
205635
238424
NVIDIA GeForce RTX 3080
183452
204325
AMD Radeon RX 6900 XT
165115
AMD Radeon RX 6800 XT
156957
NVIDIA GeForce RTX 3070 Ti
155763
158616
NVIDIA GeForce RTX 2080 Ti
149053
176497
AMD Radeon PRO W6800
137230
?
NVIDIA GeForce RTX 3070
135886
148009
NVIDIA GeForce RTX 3080 Laptop GPU
128854
138850
AMD Radeon RX 6800
127724

Source: Geekbench via @Leakbench