Nvidia GeForce RTX 4070 Ti Super

Name: Nvidia GeForce RTX 4070 Ti Super
Brand: Nvidia
SKU: 66323

Manufacturer: Nvidia

The Nvidia GeForce RTX 4070 Ti Super is a graphics card based on the Ada Lovelace architecture, produced on a 5 nm process with 45,900 million transistors. It runs at a base clock of 2340 MHz and reaches a turbo frequency of 2610 MHz, delivering 44.1 TFLOPS of floating-point performance alongside a texture rate of 689 GTexels/s and a pixel rate of 250.6 GPixel/s.

The card is equipped with 16GB of GDDR6X memory operating at an effective speed of 21,000 MHz across a 256-bit bus, resulting in a peak memory bandwidth of 672.3 GB/s. Its 8,448 shading units are complemented by 264 texture mapping units and 96 render output units, and the card supports DirectX 12 Ultimate, OpenGL 4.6, OpenCL 3, ray tracing, DLSS, stereoscopic 3D, and ECC memory. Connectivity is provided through one HDMI 2.1 port and three DisplayPort outputs, supporting up to four displays, with Intel Resizable BAR also on board. The card has a rated TDP of 285W, measures 310 mm in length and 140 mm in height, and connects via PCIe 4.

Pros

The 16GB of GDDR6X memory running at 21,000 MHz across a 256-bit bus delivers 672.3 GB/s of bandwidth, giving the card solid headroom for memory-intensive rendering tasks
A boost clock of 2610 MHz combined with 8,448 shading units and 44.1 TFLOPS of floating-point throughput provides substantial compute capacity for graphics workloads
Ray tracing and DLSS support are both present, enabling access to modern rendering techniques without additional configuration
ECC memory support adds a layer of data integrity that benefits users running compute or professional workloads alongside standard graphics tasks
Four-display support via one HDMI 2.1 port and three DisplayPort outputs gives the card meaningful flexibility for multi-monitor configurations
At 285W TDP and 310 mm in length, the card is somewhat more manageable in terms of power draw and physical footprint than larger models in its category

Cons

Air cooling is the only thermal option available, with no water-cooling support, which may limit sustained performance in poorly ventilated enclosures
There are no USB-C outputs, which restricts compatibility with monitors and devices that depend on that interface for display connectivity
XeSS (XMX) is not supported, meaning upscaling options are limited to DLSS only
RGB lighting is absent, which may matter to users building systems with coordinated lighting setups
No DVI or mini DisplayPort outputs are available, narrowing legacy display compatibility

Who is this for?

This card is a solid fit for users engaged in graphics-intensive rendering and compute workloads that benefit from 16GB of GDDR6X memory and 44.1 TFLOPS of floating-point throughput. Support for ray tracing, DLSS, and DirectX 12 Ultimate makes it well-suited for those working in modern real-time graphics pipelines or content creation environments where these features see regular use. The four-display output capability combined with ECC memory support also makes it a practical choice for multi-monitor professional setups where data reliability is a consideration.

Who is this NOT for?

Users working in space-constrained or thermally limited builds may find the 310 mm card length and 285W TDP challenging to accommodate without careful system planning. Those who depend on USB-C display connectivity will find no such output available, limiting compatibility with certain monitors and devices. Additionally, users who prioritize system aesthetics with coordinated RGB lighting will need to look elsewhere, as this card offers no lighting features whatsoever.

Performance:

GPU clock speed	2340 MHz
GPU turbo	2610 MHz
pixel rate	250.6 GPixel/s
floating-point performance	44.1 TFLOPS
texture rate	689 GTexels/s
GPU memory speed	1313 MHz
shading units	8448
texture mapping units (TMUs)	264
render output units (ROPs)	96
Has Double Precision Floating Point (DPFP)	✓
PassMark (G3D) result	31767

The card operates at a base clock of 2340 MHz, boosting up to 2610 MHz, and delivers 44.1 TFLOPS of floating-point performance alongside a texture rate of 689 GTexels/s and a pixel rate of 250.6 GPixel/s. The GPU memory runs at 1313 MHz, and the shader pipeline is built around 8,448 shading units, 264 texture mapping units, and 96 render output units. Double Precision Floating Point is supported, and the card achieves a PassMark G3D score of 31,767.

Memory:

effective memory speed	21000 MHz
maximum memory bandwidth	672.3 GB/s
VRAM	16GB
GDDR version	GDDR6X
memory bus width	256-bit
Supports ECC memory	✓

The card carries 16GB of GDDR6X memory running at an effective speed of 21,000 MHz over a 256-bit bus, producing a maximum memory bandwidth of 672.3 GB/s. ECC memory support is also included, providing data integrity coverage for workloads where memory accuracy is a requirement.

Features:

DirectX version	DirectX 12 Ultimate
OpenGL version	4.6
OpenCL version	3
Supports multi-display technology	✓
supports ray tracing	✓
Supports 3D	✓
supports DLSS	✓
has XeSS (XMX)	✕
AMD SAM / Intel Resizable BAR	Intel Resizable BAR
has LHR	✕
has RGB lighting	✕
supported displays	4

The card supports DirectX 12 Ultimate, OpenGL 4.6, and OpenCL 3, alongside ray tracing, DLSS, and stereoscopic 3D, covering a solid range of modern graphics and compute capabilities. Multi-display technology is supported with up to four simultaneous outputs, and Intel Resizable BAR is present for optimized CPU-to-GPU data access. XeSS (XMX) is not supported, LHR is not active, and there is no RGB lighting on this model.

Ports:

has an HDMI output	✓
HDMI ports	1
HDMI version	HDMI 2.1
DisplayPort outputs	3
USB-C ports	0
DVI outputs	0
mini DisplayPort outputs	0

Display connectivity is handled through one HDMI 2.1 port and three DisplayPort outputs, providing a practical range of options for connecting monitors. There are no USB-C, DVI, or mini DisplayPort outputs available on this model.

General info:

GPU architecture	Ada Lovelace
Thermal Design Power (TDP)	285W
PCI Express (PCIe) version	4
semiconductor size	5 nm
number of transistors	45900 million
Has air-water cooling	✕
width	310 mm
height	140 mm

Built on the Ada Lovelace architecture and fabricated using a 5 nm process, the card integrates 45,900 million transistors and connects to the system via PCIe 4. It carries a rated TDP of 285W and relies exclusively on air cooling, with no water-cooling option included. The card measures 310 mm in width and 140 mm in height.

Final Verdict

The Nvidia GeForce RTX 4070 Ti Super is a technically well-rounded graphics card that brings together the Ada Lovelace architecture, a 2610 MHz boost clock, and 16GB of GDDR6X memory with 672.3 GB/s of bandwidth into a package suited for demanding rendering and compute use cases. Its support for ray tracing, DLSS, DirectX 12 Ultimate, and ECC memory gives it meaningful breadth across both gaming-oriented and professional workloads, while four-display output support adds practical flexibility for multi-monitor environments. System builders should account for the 285W TDP, the 310 mm card length, and the absence of USB-C outputs or water-cooling support when planning a build around it. For those with compatible systems and the right workflow requirements, the RTX 4070 Ti Super represents a feature-complete and technically capable option within its product tier.