With up to 92 billion transistors, Blackwell is the most powerful consumer GPU ever developed. The Blackwell Streaming Multiprocessor (SM) has been updated with more processing throughput and tighter integration with the Tensor Cores to optimize the performance of neural shaders. Blackwell is enhanced with several hardware and software innovations to improve shader execution reordering. The reordering logic is twice as efficient and increases the speed and precision of reordering, accelerating the performance of neural shaders.

Built with massive AI processing power, the new Blackwell Tensor Cores support accelerated processing of FP4 precision models. With FP4, Blackwell Tensor Cores can not only process models faster, but also require less graphics memory.

To support the frame pacing requirements of the next generation of DLSS multi-frame generation, the Blackwell architecture has been equipped with enhanced hardware flip metering capabilities to provide the speed and accuracy necessary for smooth, high quality experience is required.

Blackwell also features brand new RT cores designed for ray tracing large amounts of detailed geometry. The RT cores feature twice the beam triangle cutting rate compared to the previous generation and improved compression that reduces memory requirements. This allows Blackwell GPUs to achieve levels of ray tracing geometry never before possible.

Blackwell has also been enhanced with PCIe Gen5 and DisplayPort 2.1b UHBR20, allowing displays to operate at up to 8K 165 Hz.

On GeForce RTX 50 series laptops, new Max-Q technologies such as Advanced Power Gating, Low Latency Sleep and Accelerated Frequency Switching increase battery life by up to 40% compared to the previous generation.

And to provide all this computing power, Blackwell is equipped with the world’s fastest memory – GDDR7 with speeds of up to 30Gbps. With G7 memory, Blackwell GPUs can deliver up to 1.8 TB/s of memory bandwidth.