NVIDIA has just unveiled its flagship workstation graphics card, the RTX A6000. The graphics card packs the full-fat GA102 Ampere GPU & features insane amounts of horsepower that is geared at content creation and AI applications.

NVIDIA Unleashes Its Flagship Workstation Graphics Card, The RTX A6000 With Full Fat GA102 GPU, 48 GB GDDR6 Memory & $4650 US Price

The NVIDIA RTX A6000 is one of the two Ampere powered graphics cards that is coming to the work station segment. The other is the RTX A40 and features the GA104 GPU while the RTX A6000 packs the full-fat GA102 GPU core. The RTX A6000 has been designed for the most challenging Enterprise workloads and as such, it features insane specifications.

NVIDIA RTX A6000 Graphics Card Specifications

Coming to the specifications, the RTX A6000 is powered by the full GA102 GPU core with 84 SMs or 10752 CUDA cores. NVIDIA confirmed that the card features 38.7 TFLOPs of FP32 performance. The performance rating puts the card at 8.7% faster than the RTX 3090 which has a total FP32 power of 35.58 TFLOPs. Additional performance metrics for the RTX A6000 include 75.6 TFLOPs of total RT performance and 309.7 TFLOPs of Tensor performance.

In terms of memory, the NVIDIA RTX A6000 features 48 GB of GDDR6 memory. The A6000 offers 768 GB/s speeds with its 16 Gbps memory dies. The RTX A6000 cards support vGPU with various graphics configurations starting at 1 GB up to the whole 48 GB VRAM buffer. Power is provided through the new EPS 12V 8-pin connector which is featured on the back of the card and delivers up to 300W of power to the GPU.

2 of 9

Interconnect comes in the form of the latest NVLINK which offers 112.5 GB/s (bi-directional) speeds while the native PCIe Gen 4 interface provides a 16 GB/s link. The total display options include four DisplayPort 1.4 on the A6000.

NVIDIA Workstation Graphics Card Lineup:

NVIDIA will also be shipping the card with its latest RTX Enterprise Drivers which deliver long-term stability and availability, providing enterprise customers with hardware certification from ISV's and OEMs.

Driver Name Change

With the introduction of NVIDIA RTX products powering the next generation of professional visual, compute, and AI platform solutions for the enterprise, the Quadro driver will be transitioning to the NVIDIA RTX Enterprise brand to better align with new and future products. NVIDIA RTX Enterprise drivers will continue to provide users with the same level of enterprise-class quality, reliability, performance, and security as previous Quadro drivers. These new drivers will not only deliver the latest features and improvements for NVIDIA RTX GPUs, but also for current and previous generation Quadro GPUs.

The driver branch name will also transition from “Optimal Driver for Enterprise” to “Production Branch.” All the same enterprise attributes of the driver branch will remain. The new branch name will now allow driver types to be consistently referenced across other enterprise GPU products as well, such as Data Center GPUs.

NVIDIA RTX Production Branch Driver

Release 460 is a ‘Production Branch’ (PB) release. PB drivers are designed and tested to provide long-term stability and availability, making these drivers ideal for enterprise customers and other users who require application and hardware certification from ISVs and OEMs respectively.

PB drivers are a superset of the NVIDIA Studio Drivers and provides all the benefits of the Studio Driver of the same version in addition to NVIDIA RTX-specific enhancements and testing. (via Videocardz)

The NVIDIA RTX A6000 is available through the company's OEM partners for a retail MSRP of $4650 US. The most interesting part about the pricing is that the card will retail at less than half the price of the Quadro RTX 8000 which had a launch MSRP of $10,000 US but was later adjusted down to $5500 US. Even compared to that, the RTX A6000 features better performance to dollar value since it comes with a better architecture and the same amount of VRAM.