VideoCardz has revealed a leaked slide presumably from Nvidia’s remaining presentation of its GeForce RTX 4070 graphics card. The slide reveals a remaining value of the add-in-board in addition to a few of its specs. Particularly, it says that the product will value $599 and could have a complete graphics energy of 200W.
Nvidia is anticipated to launch its GeForce RTX 4070 graphics card in mid-April, however most of its specs have been recognized for a while, albeit not from the corporate itself. The upcoming vanilla model of Nvidia’s GeForce RTX 4070 shares the AD104 graphics processor with the RTX 4070 Ti, however has solely 5888 CUDA cores working at 1920 MHz – 2475 MHz. Identical to the ‘Titanium’ model, the GeForce RTX 4070 includes a 12GB GDDR6X reminiscence subsystem with a 192-bit interface.
The brand new graphics card is claimed to have a complete graphics energy of 200W, which is considerably decrease than the TGP of Nvidia’s GeForce RTX 4070 Ti (285W) and GeForce RTX 3070 Ti (290W). This is able to allow graphics playing cards makers to miniaturize cooling methods of the GeForce RTX 4070 and due to this fact maximize compatibility with extra compact laptop instances, which will likely be one more reason why this board will possible enter the ranks of one of many finest graphics playing cards accessible. Idle energy and video playback energy of the brand new board will even be decrease in comparison with that of its predecessors, in response to the slide.
Regardless of having a closely cut-down AD104 GPU, the GeForce RTX 4070 is anticipated to provide roughly 29 FP32 TFLOPS of computational energy, which is similar to that of the GeForce RTX 3080. Nonetheless, the RTX 3080 possesses a 320-bit reminiscence bus and a powerful peak bandwidth of 760 GB/s, which is considerably larger than the 504 GB/s bandwidth offered by AD104’s 21 GT/s GDDR6X reminiscence. In reality, even a GeForce RTX 3070 Ti has greater reminiscence bandwidth (608 GB/s) than the newcomer. In the meantime, the brand new graphics card is meant to have a big L2 cache, which can possible compensate for a slower reminiscence subsystem.
| Row 0 – Cell 0 | GPU | FP32 CUDA Cores | Reminiscence Configuration | TBP | MSRP |
| GeForce RTX 4090 Ti | AD102 | 18176 (?) | 24GB 384-bit 24 GT/s GDDR6X (?) | 600W (?) | ? |
| GeForce RTX 4090 | AD102 | 16384 | 24GB 384-bit 21 GT/s GDDR6X | 450W | $1,599 |
| GeForce RTX 4080 | AD103 | 9728 | 16GB 256-bit 22.4 GT/s GDDR6X | 320W | $1,199 |
| GeForce RTX 4070 Ti | AD104 | 7680 | 12GB 192-bit 21 GT/s GDDR6X | 285W | $799 |
| GeForce RTX 4070* | AD104 | 5888 (?) | 12GB 192-bit 21 GT/s GDDR6X | 250W (?) | ? |
| GeForce RTX 4060 Ti* | AD106 | 4352 (?) | 8GB 128-bit 18 GT/s GDDR6 | 160W (?) | <$500? |
| GeForce RTX 3070 | GA104 | 5888 | 8GB 256-bit 14 GT/s GDDR6 | 220W | $499 |
Maybe an fascinating wrinkle of the slide is that Nvidia compares its GeForce RTX 4070 graphics card to its previous-generation GeForce RTX 3070 and RTX 3070 Ti choices. With its Ada Lovelace GPUs, Nvidia has been emphasizing that its newest GPUs can rival or surpass higher-class previous-generation choices at cheaper price. With its GeForce RTX 4070, it appears like Nvidia is betting on higher-performance and decrease energy on the similar launch value.
In any case, Nvidia has not introduced its GeForce RTX 4070 formally and we can not confirm authenticity of the slide. Subsequently, take the data with a grain of salt for now.