An interesting leak shared by a Taiwanese media left us with a lot of information about GeForce RTX 40 Super, NVIDIA’s next intergenerational refresh, scheduled to launch later this year. However, keep in mind that they arrive in stages, and as always, the first to land will be the strongest.

The GeForce RTX 40 Super series will use the same architecture as the current generation, meaning they will be based on Ada Lovelace and thus retain all of its key features. The changes will come at the level of specifications and the truth is that if the specifications that we will see below are confirmed, we will face one of the biggest jumps which we saw in intergenerational renewal.

To better understand this jump, we will compare the specifications of the GeForce RTX 40 with the possible specifications of the GeForce RTX 40 Super. Keep in mind that even if they are not confirmed, they make a lot of sense, and the truth is that they are totally believable.

GeForce RTX 40 vs. GeForce RTX 40 Super

GeForce RTX 4060

• Graphics core AD107 in 5nm.
• 3072 shaders at 2.5 GHz.
• 96 texturing units.
• 32 raster units.
• 96 tensor cores of the fourth generation.
• 24 cores of the third generation RT.
• 128-bit memory bus.
• 8 GB GDDR6 with 272 GB/s bandwidth.
• 15 TFLOPs of performance in FP32.
• 24 MB L2 cache.
• 115W TGP.

GeForce RTX 4060 Super

• Graphics core AD104 in 5nm.
• 5,120 shaders at an unspecified frequency.
• 160 texturing units.
• 64 raster units.
• 160 tensor cores of the fourth generation.
• 40 cores of the 3rd generation RT.
• 192-bit memory bus.
• 12 GB GDDR6 with 432 GB/s bandwidth.
• 200W TGP.

GeForce RTX 4070

• Graphics core AD104 in 5nm.
• 5,888 shaders at 1,920 MHz-2,475 MHz, normal and turbo mode.
• 184 texturing units.
• 184 tensor kernels of the fourth generation.
• 64 raster units.
• 46 cores of the third generation RT.
• Performance in FP32: 29.15 TFLOPs.
• 192-bit bus.
• 12 GB GDDR6X 21 GHz memory.
• Bandwidth 504.2 GB/s.
• 36 MB L2 cache.
• 200W TGP.

GeForce RTX 4070 Super

• Graphics core AD103 in 5nm.
• 8,192 shaders at an unspecified frequency.
• 256 texturing units.
• 96 raster units.
• 256 tensor cores of the fourth generation.
• 64 cores of the third generation RT.
• 256-bit memory bus.
• 16 GB GDDR6 with 672 GB/s bandwidth.
• TGP 280W.

GeForce RTX 4080

• AD103 GPU manufactured by 5nm process (TSMC).
• 9728 shaders at 2205MHz-2505MHz, normal and turbo mode.
• 304 texturing units.
• 96 raster units.
• 304 fourth generation tensor core.
• 76 cores of the 3rd generation RT.
• 256-bit bus.
• 16 GB of GDDR6X memory at 22.4 Gbps.
• 65 MB L2 cache.
• Bandwidth 716.8 GB/s.
• Performance in FP32: 48.74 TFLOPs.
• TGP 320W.

GeForce RTX 4080 Super

• Graphics core AD102 in 5nm.
• 13,312 shaders at an unspecified frequency.
• 416 texturing units.
• 128 raster units.
• 416 tensor kernels of the fourth generation.
• 104 RT cores of the 3rd generation.
• 320-bit memory bus.
• 20 GB GDDR6 with 840 GB/s bandwidth.
• TGP 350W.

GeForce RTX 4090

• AD102 GPU manufactured by 5nm process (TSMC).
• 16,384 shaders at 2,235 MHz-2,520 MHz, normal and turbo mode.
• 512 texturing units.
• 176 raster units.
• 512 fourth generation tensor cores.
• 128 cores 3rd generation RT.
• 384-bit bus.
• 24 GB of GDDR6X memory at 21 Gbps.
• It uses the PCIe Gen4 standard in x16 mode.
• 72 MB L2 cache.
• Bandwidth 1008 GB/s.
• Performance in FP32: 82.58 TFLOPs.
• TGP: 450 watts.

GeForce RTX 4090 Super

• Graphics core AD102 in 5nm.
• 18,432 shaders at an unspecified frequency.
• 576 texturing units.
• 192 raster units.
• 576 tensor kernels of the fourth generation.
• 144 RT cores of the 3rd generation.
• 384-bit memory bus.
• 24 GB GDDR6 with a bandwidth of 1152 GB/s.
• 450W TGP.

GeForce RTX 40 Super not only would they be much stronger than the GeForce RTX 40, which is already evident when looking at the compared specs of each model we’ve just seen, but also They will have more graphics memory. After the criticism that NVIDIA receives for continuing to bet on 8GB graphics memory configurations in the mid-range and even the high-end range, this would be a rather intelligent response from the green giant.

For example, the GeForce RTX 4060 will have the configuration 3072 shaders and 8 GB of graphics memory with a 128-bit bus and a GeForce RTX 4060 will theoretically have 5,120 shaders and 12 GB of graphics memory over a 192-bit bus. This spec upgrade will be so significant that its raw performance could be on par with the GeForce RTX 3070 Ti, or maybe a bit higher.

The GeForce RTX 4070 Super and GeForce RTX 4080 Super would also receive huge improvements over the current models, both due to the increased number of shaders and the increased amount of memory and bandwidth. When GeForce RTX 4070 Super would be more powerful than GeForce RTX 4070 Ti and it would also be above the GeForce RTX 3090 Ti, while the GeForce RTX 4080 Super could come very close to the GeForce RTX 4090.

Possible prices of GeForce RTX 40 Super

According to the source, the price will be GeForce RTX 4060 399 dollarswill the GeForce RTX 4070 Super cost 699 dollars and GeForce RTX 4080 Super and 4090 Super will be priced $1,199 and $1,999.

In general, the prices are quite reasonable and in some cases would match the introductory prices of current models. To make a direct comparison, I remind you that the GeForce RTX 4060 will hit the market in July with an MSRP of $299; The GeForce RTX 4070 had a suggested retail price of $599, and the GeForce RTX 4080 and RTX 4090 cost $1,199 and $1,599, respectively. We would see the biggest price increase for the GeForce RTX 4090 Super.