NVIDIA has introduced the GeForce RTX 5090, GeForce RTX 5080, GeForce RTX 5070 Ti and GeForce RTX 5070: the top cards in its GeForce RTX 50 series consumer GPUs.

The GPUs, all of which will be available in February and range in price from $1,999 to $549, are the first desktop cards to utilize NVIDIA’s next-generation Blackwell GPU architecture.

Although they are primarily gaming cards, NVIDIA also sells the RTX 50 series to artists. Therefore, we have summarized the most important specifications for DCC work and performance comparisons for CG software below.

NVIDIA’s GeForce RTX 50 series GPUs and previous generation counterparts
	RTX 5090	RTX 4090	RTX 5080	RTX 4080	RTX 5070 Ti	RTX 4070 Ti	RTX 5070	RTX 4070
architecture	Blackwell	Ada Lovelace	Blackwell	Ada Lovelace	Blackwell	Ada Lovelace	Blackwell	Ada Lovelace
CUDA cores	21,760	16,384	10,752	9,728	8,960	7,680	6,144	5,888
Tensor cores*	680	512	336	304	280	240	192	184
RT cores*	170	128	84	76	70	60	48	46
Base clock (GHz)	2.41	2.23	2.62	2.21	2.45	2.31	2.51	1.92
Boost clock (GHz)	2.01	2.52	2.30	2.51	2.30	2.61	2.16	2.48
Computing power FP32 (Tflops)*	104.8	82.6	56.3	48.7	44.4	40.1	31.0	29.2
GPU memory	32GB GDDR7	24GB GDDR6X	16GB GDDR7	16 GB GDDR6X	16GB GDDR7	12GB GDDR6X	12GB GDDR7	12GB GDDR6X
TGP	575W	450W	360W	320W	300W	285W	250W	200W
Release date	2025	2022	2025	2022	2025	2023	2025	2023
RRP at launch	$1,999	$1,599	$999	$1,199	$749	$799	$549	$599

*Data comes from third party websites.

Important specifications for DCC work
In terms of core specs, the new GeForce RTX 50 Series GPUs represent a significant improvement over their current-generation GeForce RTX 40 Series counterparts.

All have higher counts of the three main hardware core types: CUDA for general GPU computation, Tensor for AI operations, and RT for hardware-accelerated ray tracing.

The RT cores are also now fourth generation and the Tensor cores are fifth generation, although NVIDIA has not yet revealed many details about how this will affect GPU rendering performance.

What will definitely impact GPU rendering is the increased GPU memory capacity of the top-end GeForce RTX 5090: up to 32GB, up from 24GB on the current RTX 4090 generation.

The GeForce RTX 5070 Ti also has more GPU memory than its predecessor, although there is no change in either the GeForce RTX 5080 or the GeForce RTX 5070.

Additionally, the entire GeForce 50 series uses the latest GDDR7 memory rather than the older GDDR6X memory that was used in the GeForce RTX 40 series.

There are fewer changes in display connectivity: the GeForce 50 series cards have one HDMI and three DisplayPort ports, just like the GeForce RTX 40 series.

However, they support DisplayPort 2.1, the latest version of the standard – and will support the upcoming DisplayPort 2.1b – while the GeForce RTX 40 series supports DisplayPort 1.4a.

These increases in processing power come with a corresponding increase in power consumption – all four cards in the GeForce RTX 50 series have higher overall graphics performance than their predecessors.

However, they are also more compact – unlike the high-end GeForce RTX 40 series, they are all dual-slot cards – and most of them are cheaper than their predecessors, at least at launch.

The exception is the GeForce RTX 5090, whose launch price is $1,999, $400 more than the GeForce RTX 4090, even though NVIDIA says it offers twice the overall performance.

Benchmarks and performance in DCC applications
Since the GeForce RTX 50 series are gaming cards, most of the performance comparisons published by NVIDIA are for gaming and not CG software.

An exception is the architectural GPU renderer D5 Render.

The comparison table above shows a more than 2x performance increase for the GeForce RTX 5090 compared to the current RTX 4090 generation, presumably using the standard D5 rendering benchmark.

Although NVIDIA published a blog post about how the new cards will impact creative workflows, it focuses heavily on generative AI and not DCC software.

However, there is a section on video editing and video production that claims the GeForce RTX 5090 can export videos “60% faster” than the current-gen GeForce RTX 4090.

The comparison table above is from a DaVinci Resolve video, although the blog post also mentions Premiere Pro.

Prices and release dates
The GeForce RTX 5090 and 5080 will be available on January 30th, priced at $1,999 and $999, respectively.

The GeForce RTX 4070 Ti and 4070 will be available in February, priced at $749 and $549, respectively.

Read NVIDIA’s announcement of the GeForce RTX 50 series GPUs

Specifications for the GeForce RTX 50 series GPUs can be found on the NVIDIA website

Have your say on this story by following the CG channel on Facebook, Instagram and more X (formerly Twitter). In addition to commenting on stories, followers of our social media accounts can also see videos that we do not publish on the website itself, including making-ofs for the latest VFX films, animations, game films and motion graphics -Projects.