The NVIDIA AD104 'Ada' GPU which will be featured on the upcoming GeForce RTX 4070 Ti graphics card has been pictured.
NVIDIA AD104 GPU Pictured, The Ada GPU To Power The GeForce RTX 4070 Ti Graphics Card
The picture of the NVIDIA AD104 'Ada' GPU has been leaked by MEGAsizeGPU and for comparison purposes, a single GDDR6(X) memory chip has been placed side by side. The GPU will be the most smallest amongst the three Ada GPUs, the AD102 and AD103. We can see that this particular SKU is labeled as the AD104-400-A1 which means that it is utilizing the fully enabled die. This die will get utilized within the upcoming GeForce RTX 4070 Ti which is a rebadge of the 'Unlaunched' RTX 4070 Ti graphics card.
Our Twitter friend, Harukaze5719, managed to do a quick die measurement and it looks like the die could measure around 300 mm2 (294.5 mm2 to be precise). This is not the official die size but that is also close to this figure as NVIDIA has officially confirmed. At 295mm2, the GPU should end up around 25% smaller than GA104, its Ampere-based predecessor. This is also about the same die size as the single Navi 31 GCD.
— 포시포시 (@harukaze5719) November 30, 2022
The AD103 GPU already offers some of the best power efficiency of any gaming graphics card that we have tested yet and we can expect the same from the AD104 GPU. The AD103 GPU averages at 250W while gaming so if the AD104 GPU can end up around the 200W power budget while gaming, that would be a treat for power-conscious gamers.
NVIDIA AD104 vs GA104 GPU Comparison (Image Credits: MEGAsizeGPU / TechPowerUP):
NVIDIA GeForce RTX 4070 Ti 12 GB 'Official' Specifications
The NVIDIA GeForce RTX 4070 Ti will utilize the "Ada Lovelace" AD104-400 GPU configuration with 7,680 cores or 60 SMs enabled which is the full-fat SKU. The GPU will be packing 48 MB of L2 cache and features a 192-bit bus interface so that's why we are getting up to 12 GB of GDDR6X capacities. The memory is said to be running at 21 Gbps speeds for a memory bandwidth of 504 GB/s. The card is said to be clocked at a 2610 MHz boost clock however the peak frequency will be higher.
- NVIDIA GeForce RTX 4070 Ti 12 GB "Official" TBP - 285W
- NVIDIA GeForce RTX 3070 Ti 8 GB "Official" TBP - 290W
For power, the TBP is now set to be rated at 285W which is a 35W decrease versus the RTX 3080 10 GB model and a 5W decrease from the RTX 3070 Ti. The new graphics card is expected to offer better performance than the RTX 3080 but given the specs cut over the 4080 16 GB, there will be a big gap between both models of around 30-40%.
The most important question is whether NVIDIA will be using the same $899 US pricing for its graphics card or tone down the pricing a bit. We know from benchmarks that the GeForce RTX 4080 12 GB was about on par with the RTX 3090 Ti & faster in a few cases when RT or DLSS was used. AMD is promising up to 40-50% gains with its RX 7900 XT over the 6950 XT at a price of $899 US. So it will be a heated battle between the two cards. But AMD will release their cards a few weeks earlier in December so they will have an advantage there.
The NVIDIA GeForce RTX 4070 Ti graphics card will be the first to utilize the AD104 GPU and will be unveiled on 3rd January followed by an official launch on the 5th of January as we reported here.
NVIDIA GeForce RTX 40 Series Official Specs:
| Graphics Card Name | NVIDIA GeForce RTX 4090 | NVIDIA GeForce RTX 4090 D | NVIDIA GeForce RTX 4080 | NVIDIA GeForce RTX 4070 Ti | NVIDIA GeForce RTX 4070 | NVIDIA GeForce RTX 4060 Ti | NVIDIA GeForce RTX 4060 |
|---|---|---|---|---|---|---|---|
| GPU Name | Ada Lovelace AD102-300 | Ada Lovelace AD102-250 | Ada Lovelace AD103-300 | Ada Lovelace AD104-400 | Ada Lovelace AD104-250 | Ada Lovelace AD106-350 | Ada Lovelace AD107-400 |
| Process Node | TSMC 4N | TSMC 4N | TSMC 4N | TSMC 4N | TSMC 4N | TSMC 4N | TSMC 4N |
| Die Size | 608mm2 | 608mm2 | 378.6mm2 | 294.5mm2 | 294.5mm2 | 190.0mm2 | 146.0mm2 |
| Transistors | 76 Billion | 76 Billion | 45.9 Billion | 35.8 Billion | 35.8 Billion | 22.9 Billion | TBD |
| CUDA Cores | 16384 | 14592 | 9728 | 7680 | 5888 | 4352 | 3072 |
| TMUs / ROPs | 512 / 176 | TBD | 320 / 112 | 240 / 80 | 184 / 64 | 136 / 48 | TBD |
| Tensor / RT Cores | 512 / 128 | 456 / 128 | 304 / 76 | 240 / 60 | 184 / 46 | 136 / 34 | TBD |
| L2 Cache | 72 MB | 72 MB | 64 MB | 48 MB | 36 MB | 32 MB | 24 MB |
| Base Clock | 2230 MHz | 2280 MHz | 2210 MHz | 2310 MHz | 1920 MHz | 2310 MHz | 1830 MHz |
| Boost Clock | 2520 MHz | 2520 MHz | 2510 MHz | 2610 MHz | 2475 MHz | 2535 MHz | 2460 MHz |
| FP32 Compute | 83 TFLOPs | TBD | 49 TFLOPs | 40 TFLOPs | 29 TFLOPs | 22 TFLOPs | 15 TFLOPs |
| RT TFLOPs | 191 TFLOPs | TBD | 113 TFLOPs | 82 TFLOPs | 67 TFLOPs | 51 TFLOPs | 35 TFLOPs |
| Tensor-TOPs | 1321 TOPs | TBD | 780 TOPs | 641 TOPs | 466 TOPs | 353 TOPs | 242 TOPs |
| Memory Capacity | 24 GB GDDR6X | 24 GB GDDR6X | 16 GB GDDR6X | 12 GB GDDR6X | 12 GB GDDR6X | 8-16 GB GDDR6 | 8 GB GDDR6 |
| Memory Bus | 384-bit | 384-bit | 256-bit | 192-bit | 192-bit | 128-bit | 128-bit |
| Memory Speed | 21.0 Gbps | 21.0 Gbps | 23.0 Gbps | 21.0 Gbps | 21.0 Gbps | 18.0 Gbps | 17.0 Gbps |
| Bandwidth | 1008 GB/s | 1008 GB/s | 736 GB/s | 504 GB/s | 504 GB/s | 288 GB/s (554 GB/s Effective) | 272 GB/s (453 GB/s Effective) |
| TBP | 450W | 425W | 320W | 285W | 200W | 160-165W | 115W |
| Price (MSRP / FE) | $1599 US / 1949 EU | 12,999 RMB (China-Only) | $1199 US / 1469 EU | $799 US | $599 US | $399-$499 US | $299 US |
| Price (Current) | $1599 US / 1859 EU | 12,999 RMB (China-Only) | $1199 US / 1399 EU | $799 US | $599 US | $399-$499 US | $299 US |
| Launch (Availability) | 12th October 2022 | 28th December 2023 | 16th November 2022 | 5th January 2023 | 13th April 2023 | 24th May / 18th July 2023 | 29th June 2023 |
