Nvidia is giving away five classic GPUs personally signed by CEO Jensen Huang – the first two are the GeForce 256 and GeForce 8800 Ultra

Ahead of CES 2025, Nvidia will be giving away five classic GPUs signed by CEO Jensen Huang. The trillion-dollar GPU giant has released its first two graphics card giveaways on Xequipped with GeForce 256 and GeForce 8800 Ultra cards.

The giveaway is taking place under the “GeforceGreats” hashtag, which Nvidia has set for all of its content related to CES 2025. Both GPUs are installed in a black display that features Jensen’s signature in gold script in the lower right corner. To win, comment on each X post.

Nvidia strategically chooses these two specific GPUs to give away the first and second (of five) classic GPUs. The GeForce 256 was Nvidia’s first-ever GeForce graphics processor and the first-ever graphics card to be sold under the GPU moniker (graphics cards were previously called “3D” cards). The GeForce 8800 Ultra was the first CUDA GPU introduced to the global market. This technology would become one of the most valuable and popular Nvidia technologies the company has ever created, shaping the way GPUs are used even today.

The Geforce 256 was released in 1999, at the height of the Internet boom and the beginning of up-to-date 3D graphics rendering functionality in computers. The graphics processor is equipped with as many as four (yes, only four) pixel shaders, four TMUs and four ROPs. It had 32 MB of memory and ran on a 64-bit memory bus with a bandwidth of 1.144 GB/s. The GPU had one VGA output and supported DirectX 7.0 and OpenGL 1.2.

The GeForce 256 represented a change in the way we thought about graphics cards. Previously, all graphics cards were called “3D” cards because they were designed specifically for 3D rendering and were often less elaborate than CPUs. However, the GeForce 256 was a different beast as it had 23 million transistors in the same range as the top processors of the time such as AMD Athlon processors and Intel Pentium III processors. A few years later, this was the precursor to CUDA, when GPUs began to compete directly with CPUs, performing the same calculations as CPUs.

The huge number of transistors in the GeForce 256 at that time was supplemented with support for fresh graphics technology. One of these technologies at the time was support for the fresh Transform and Lighting Engine. This technology enabled the GeForce 256 to convert a 3D scene and all its objects from “world space” to “screen space”, essentially transforming the resources from the 3D engine into a perceptible image on the screen.

Before the 256, this workload was very CPU-intensive. “3D” graphics cards often wait for the processor to complete this task. With this functionality built into the GeForce 256, the GPU can get the job done, improving performance and enabling developers to push the boundaries of 3D rendering further than ever before.

The GeForce 8800 Ultra, launched in 2007, includes 128 shader cores, 32 TMUs, 24 ROPs, 16 SMs, 96 KB L2 cache, 612 MHz core clock, 1512 MHz shader clock, and a 384-bit memory bus with 768 MB of memory GDDR3 and 104 GB/s memory bandwidth. It was the flagship GPU running on the Tesla G80 GPU, the first core and first GPU architecture to support CUDA, supporting DirectX 11.1 and the Shader Model 4.0 standard.

CUDA is one of the most crucial technologies that Nvidia has ever produced. This key technology has forever changed the way GPUs are used, allowing them to perform general-purpose calculations that the same CPUs can perform. The first generation of CUDA supported C code and required a dedicated CUDA driver to run.

CUDA has become the dominant method for executing general-purpose computing tasks that heavily benefit from parallelism in enterprise applications. CUDA ushered in the era of general-purpose GPUs, where GPUs were no longer used solely for graphics acceleration, but as general-purpose, multi-function processing units.