NVIDIA RTX 50 Series Officially Announced, A New Era of Graphics Performance

7 Jan 2025

NVIDIA introduces the RTX 50 series, a new lineup of GPUs based on the Blackwell architecture, offering improved performance, advanced features, and a range of pricing options.

NVIDIA has introduced the RTX 50 series, a new lineup of GPUs based on the Blackwell architecture. This series delivers improved performance, updated features, and a range of pricing options. The initial launch includes the flagship RTX 5090, alongside the RTX 5080, RTX 5070 Ti, and RTX 5070. Two additional mid-range models—the RTX 5060 Ti and RTX 5060—are expected to debut later in 2025. Here's a closer look at each GPU in the series.

Credit: Nvidia

NVIDIA GeForce RTX 5090: The Ultimate Powerhouse

The NVIDIA GeForce RTX 5090 leads the lineup with 21,760 CUDA cores, a 33% increase over the RTX 4090. This flagship model features 32GB of GDDR7 memory on a 512-bit bus, offering a bandwidth of 1,792 GB/s. It operates at clock speeds of 2.41 GHz and has a total board power of 575W, making it a top choice for gaming and professional workloads.

Credit: Nvidia

NVIDIA GeForce RTX 5080: High-End Gaming

The RTX 5080 is built with the GB203 GPU and includes 10,752 CUDA cores. With clock speeds of 2.62 GHz, it provides high performance suitable for 4K gaming and intensive creative workloads. The card includes 16GB of GDDR7 memory on a 256-bit bus, delivering 960 GB/s of bandwidth. Priced at $999, the RTX 5080 offers twice the performance of the RTX 4080 SUPER and includes updates such as DLSS 4 and PCIe 5.0 support. It will be available starting January 30, 2025.

Credit: Nvidia

NVIDIA GeForce RTX 5070 Ti: Mid-Range

The RTX 5070 Ti is designed for gamers seeking high performance at a reasonable price. This GPU is powered by a cut-down version of the GB203 GPU, offering 8,960 CUDA cores and clock speeds of 2.45 GHz. With 16GB of GDDR7 memory on a 256-bit bus, it achieves a bandwidth of 896 GB/s. At $749, the RTX 5070 Ti delivers twice the performance of the RTX 4070 Ti and supports advanced features like DLSS 4, making it an excellent choice for 1440p and even 4K gaming. The RTX 5070 Ti will hit shelves in February 2025.

NVIDIA GeForce RTX 5070: Budget Performance Leader

The RTX 5070 completes the initial lineup with the GB205 GPU, 6,144 CUDA cores, and 12GB of GDDR7 memory on a 192-bit bus, providing a bandwidth of 672 GB/s. With a TBP of 250W and clock speeds of 2.51 GHz, this card surpasses the RTX 4090 in certain benchmarks. Priced at $549, the RTX 5070 is designed for gamers aiming for high performance at 1440p. It will be available starting February 2025.

What’s Next: RTX 5060 Ti and RTX 5060

Two additional models, the RTX 5060 Ti and RTX 5060, are expected to launch in March or April 2025. Both cards are confirmed to include GDDR7 memory, PCIe 5.0 support, and strong performance for their price points, with additional details to be announced.

Features Across the Lineup

• DLSS 4: NVIDIA’s latest AI-driven upscaling technology
• GDDR7 Memory: Faster speeds and improved efficiency over GDDR6
• PCIe 5.0: High-speed connectivity for future workloads
• DisplayPort 2.1a: Supports ultra-high resolutions and refresh rates for next-gen displays

Availability and Pricing

The RTX 5090 and RTX 5080 will launch on January 30, 2025, followed by the RTX 5070 Ti and RTX 5070 in February. Prices start at $549 for the RTX 5070, scaling up to $1,999 for the RTX 5090. Custom variants and NVIDIA Founders Edition models will be available for all cards.