NVIDIA has just announced its new RTX A4500 workstation GPU, which uses the GA102 GPU with 7168 CUDA cores and 20GB of GDDR6 memory.
The introduction of the new NVIDIA RTX A4500 workstation GPU offers its 7168 CUDA cores alongside 224 Tensor Cores, and 20GB of GDDR6 memory clocked at 16Gbps on a 320-bit memory bus which will deliver up to 640GB/sec of memory bandwidth.
NVIDIA says the new RTX A4500 workstation GPU will have 23.7 TFLOPs of FP32 compute performance, while it has 46.2 TFLOPs of RT performance. NVIDIA's new RTX A4500 workstation GPU has a 200W TDP, which is 15% lower than the RTX A5000 and 17% slower.
Alongside the new RTX A4500 workstation GPU, NVIDIA announces the new RTX A2000 workstation GPU which uses the GA106 GPU with 3328 CUDA cores and up to 8 TFLOPs of single-precision compute performance. NVIDIA uses 12GB of GDDR6 on the RTX A2000 GPU, with a much lower TDP of just 70W.
Both cards are available for desktop workstation systems, with 4 x DisplayPort 1.4 connectors for some major monitor hook-up-age.