KitGuru KitGuru.net – Tech News | Hardware News | Hardware Reviews | IOS | Mobile | Gaming | Graphics Cards
When Nvidia announced the RTX 40-series Super refresh, my eyes were instantly drawn to the RTX 4070 Ti Super. It may have a somewhat ridiculous name, but by offering 16GB VRAM and a 256-bit memory interface, it answers one of the main criticisms levelled at the other xx70 SKUs, namely the memory capacity. Factoring in the 10% boost in CUDA cores as well as the fact that the 4070 Ti Super launches at the same price as the RTX 4070 Ti, and we certainly have potential for this to be one of the best 40-series GPUs yet.
While it's true that the Nvidia RTX 4070 Ti Super is launching at the same $799 MSRP as the original RTX 4070 Ti, in the UK the situation is even better. The 4070 Ti launched at £799 on these shores, but due to changing exchange rates, the 4070 Ti Super lands at £769, so it should be both faster and cheaper than the GPU it replaces.
It's also worth making clear that, as with the 4070 Ti launch, there is no Founders Edition model for the 4070 Ti Super. Instead, we were sent the MSI Ventus 3X model, which is designed to be an MSRP card according to Nvidia. Let's find out what it has to offer…
If you want to read this review as a single page, click HERE.
| RTX 4080 | RTX 4070 Ti Super | RTX 4070 Ti | RTX 4070 Super | RTX 4070 | |
| Process | TSMC N4 | TSMC N4 | TSMC N4 | TSMC N4 | TSMC N4 |
| SMs | 76 | 66 | 60 | 56 | 46 |
| CUDA Cores | 9728 | 8448 | 7680 | 7168 | 5888 |
| Tensor Cores | 304 | 264 | 240 | 224 | 184 |
| RT Cores | 76 | 66 | 60 | 56 | 46 |
| Texture Units | 304 | 264 | 240 | 224 | 184 |
| ROPs | 112 | 96 | 80 | 80 | 64 |
| GPU Boost Clock | 2505 MHz | 2610 MHz | 2610 MHz | 2475 MHz | 2475 MHz |
| Memory Data Rate | 22.4 Gbps | 21 Gbps | 21 Gbps | 21 Gbps | 21 Gbps |
| L2 Cache | 65536 KB | 49152 KB | 49152 KB | 36864 KB | 36864 KB |
| Total Video Memory | 16GB GDDR6X | 16GB GDDR6X | 12GB GDDR6X | 12GB GDDR6X | 12GB GDDR6X |
| Memory Interface | 256-bit | 256-bit | 192-bit | 192-bit | 192-bit |
| Memory Bandwidth | 716.8 GB/Sec | 672 GB/Sec | 504 GB/Sec | 504 GB/Sec | 504 GB/Sec |
| TGP | 320W | 285W | 285W | 220W | 200W |
First, a quick spec recap. Unlike the RTX 4070 Ti and RTX 4070 Super which are based on AD104 silicon, the new 4070 Ti Super uses a cut-down AD103 die, measuring 379mm2. The fundamental building blocks are still the same of course, with the RTX 4070 Ti Super offering a total of 66 Streaming Multiprocessors (SMs), each housing 256 CUDA Cores, for a total of 8448. We also find 66 RT cores, 264 Tensor cores, 264 Texture Units, and 96 ROPs.
TSMC's N4 node has Nvidia cranking up the clock speed significantly this generation, with the RTX 4070 Ti Super sporting the same 2610MHz rated boost clock as the 4070 Ti. That's 95MHz faster than the rated clock speed of the RTX 4080, but we would expect GPU Boost to push things further still.
The memory configuration is arguably the biggest upgrade over the other xx70 series SKUs. Moving to AD103 means the 4070 Ti Super comes equipped with a 256-bit memory interface, paired with 16GB GDDR6X running at 21Gbps, putting total memory bandwidth at 672 GB/s. L2 cache remains the same as the RTX 4070 Ti, with 49152KB.
Considering the increased core-count, it's interesting that power draw remains the same as the RTX 4070 Ti, with the new Super model still boasting a 285W TGP. This is something we focus on closely in this review, using our enhanced GPU power testing methodology, so read on for our most detailed power and efficiency testing yet.
Be sure to check out our sponsors store EKWB here
