NVIDIA GeForce RTX 4060 Ti
An Ada Lovelace graphics card with 4,352 CUDA cores, 16 GB or 8 GB of GDDR6 on a 128-bit bus, DLSS 3, a 165 W or 160 W board power and a single 8-pin connector.

Full Specification Sheet
| Architecture | NVIDIA Ada Lovelace |
|---|---|
| CUDA Cores | 4,352 |
| Boost / Base Clock | 2.54 GHz / 2.31 GHz |
| Memory | 16 GB or 8 GB GDDR6, 128-bit |
| Tensor Cores | 4th generation, 353 AI TOPS |
| RT Cores | 3rd generation, 51 RT TFLOPS |
| Shader Throughput | 22 TFLOPS |
| Interface | PCI Express Gen 4 |
| Board Power | 165 W or 160 W (Founders Edition or reference design) |
| Required System Power | 550 W |
| Power Connector | 1x PCIe 8-pin (adapter in box) or 300 W or greater PCIe Gen 5 cable |
| Display Outputs | HDMI 2.1a, 3x DisplayPort 1.4a; up to 4 displays |
| Founders Edition Size | 244 mm long, 112 mm wide, 2-slot |
The NVIDIA GeForce RTX 4060 Ti is a mid-range graphics card from the GeForce RTX 40 series, built on the Ada Lovelace architecture. NVIDIA presents it together with the GeForce RTX 4060 as a family for gaming, streaming and creating, and describes the architecture as ultra-efficient. The 4060 Ti is the upper model of the pair: it has more CUDA cores, higher clocks and a faster memory configuration than the RTX 4060, and it is offered in a 16 GB and an 8 GB memory version. This page collects the specification NVIDIA publishes for the Founders Edition and reference design, explains what the numbers mean and marks clearly which claims are NVIDIA's own. There is no price on the page, and we make no benchmark claims.
Architecture and core counts
The card has 4,352 CUDA cores, the general-purpose shader units that execute graphics and compute work. NVIDIA lists a base clock of 2.31 GHz and a boost clock of 2.54 GHz, and states throughput of 22 TFLOPS for the shader cores, 51 TFLOPS for the third-generation RT cores and 353 AI TOPS for the fourth-generation Tensor cores. TFLOPS and TOPS are theoretical peak rates and not a prediction of frame rates. For comparison, the RTX 4060 listed on the same page has 3,072 CUDA cores, a 2.46 GHz boost clock, 15 shader TFLOPS, 35 RT TFLOPS and 242 AI TOPS. NVIDIA's marketing for the architecture makes three headline claims: new streaming multiprocessors with up to twice the performance and power efficiency, fourth-generation Tensor cores with up to four times the performance using DLSS 3 compared with brute-force rendering, and third-generation RT cores with up to twice the ray tracing performance. These are NVIDIA's comparative claims against the previous generation and depend on the test conditions.
Memory: 16 GB or 8 GB
The standard memory configuration is listed as 16 GB of GDDR6 or 8 GB of GDDR6, both on a 128-bit memory interface. Memory capacity matters for texture-heavy games and for creative applications, and the two versions are the same GPU with a different amount of memory, so check the exact product before buying. Our guide to 8 GB versus 24 GB of video memory explains when capacity limits performance and when it does not. The 128-bit memory interface is the width NVIDIA lists for both memory versions, and the page gives no further detail on memory bandwidth, so we do not quote any.
DLSS 3, ray tracing and Reflex
The card supports NVIDIA DLSS 3.5, which the specification table lists as Super Resolution, DLAA, Ray Reconstruction and Frame Generation. NVIDIA explains that DLSS 3 uses the fourth-generation Tensor cores and the Optical Flow Accelerator to create additional frames with AI and improve image quality. The card also supports NVIDIA Reflex, which the manufacturer says optimises and measures system latency, and ray tracing through the third-generation RT cores. NVIDIA states that over 500 top games and applications use RTX. Whether a particular game uses these features is up to the developer, and they change image quality and latency rather than raw shader power.
Display and video capabilities
Display outputs are one HDMI 2.1a and three DisplayPort 1.4a connectors, supporting up to four independent displays at 4K and 120 Hz using DisplayPort or HDMI, or two at 4K and 240 Hz, or 8K at 60 Hz with Display Stream Compression. The maximum single-display resolution is listed as 4K at 240 Hz or 8K at 60 Hz with DSC. HDCP 2.3 is supported. The card has one eighth-generation NVIDIA encoder with AV1 encode and one fifth-generation decoder with AV1 decode. NVIDIA highlights AV1 encoding as more efficient than H.264 for live streaming, which is relevant for creators who broadcast. The NVIDIA Broadcast app, RTX Video Super Resolution for supported browsers, NVIDIA Studio drivers and the Omniverse platform are all listed as supported features.
Power and cooling
Total graphics power is listed as 165 W or 160 W, and the page lists a required system power of 550 W, based on a PC with a Ryzen 9 5900X processor; NVIDIA adds that requirements can differ with the system configuration. The card needs one PCIe 8-pin cable, with an adapter in the box, or a PCIe Gen 5 cable of 300 W or more, and certain partner models may use one 8-pin connector. That low requirement makes the card easy to fit into an existing system, but our guide to power supply wattage shows how to check the rest of your build. The maximum GPU temperature is 90 degrees Celsius. NVIDIA also publishes idle power of 7 W, video playback power of 13 W and average gaming power of 140 W, measured across 22 games at 4K, 1440p and 1080p on the Founders Edition or reference design; the RTX 4060 is listed at 11 W and 110 W for the last two.
Size and compatibility
The Founders Edition is 244 mm long, 112 mm wide and occupies two slots, while partner cards vary in size, so check the length and thickness against the case. The card uses a PCI Express Gen 4 interface, and NVIDIA lists Resizable BAR support, a feature that lets the processor access the entire graphics memory at once, as well as G-SYNC, NVIDIA App or GeForce Experience, ShadowPlay, DirectX 12 Ultimate, Vulkan and OpenGL 4.6. Multi-GPU NVLink is not supported. The card is listed as VR ready.
Founders Edition versus partner cards
NVIDIA is explicit that the published figures represent the Founders Edition or reference design, and that clock specifications apply while gaming with medium to full GPU utilisation. Graphics card specifications may vary by add-in-card manufacturer, whose own websites hold the actual shipping specifications. In practice this means that a partner card may have a higher factory boost clock, a different cooler, a different length and even a different power connector arrangement than the numbers above. It also means that the 16 GB and 8 GB versions can differ between manufacturers in cooling design and price. When you compare two specific products, always compare the partner's own specification sheets, and treat the NVIDIA table as the baseline for the GPU itself.
Where it fits
The GeForce RTX 4060 Ti is aimed at 1080p and 1440p gaming with ray tracing and DLSS in the mid-range, with the larger 16 GB version attractive for people who care about memory capacity. Within the range, see our explanation of the xx60, xx70 and xx80 naming tiers for how the model names map to positioning. For a comparison with the previous generation's 12 GB card, see the RTX 4060 Ti versus RTX 3060 12GB comparison, and if you want to step up, the GeForce RTX 4070 page. You can browse all cards in the graphics card category. None of the statements above is a test result; all values are NVIDIA's published specifications.
Product image: NVIDIA product image.


