The next generation graphics cards from NVIDIA, which include the GeForce RTX 5080 and RTX 5090 are expected to hit the ground running when they launch, with the 5080 expected to have the fastest GDDR7 memory in a graphics card currently available at 32 Gbps thanks to the GB203 GPU code and 16 GB of GDDR7 memory.
When compared to the existing RTX 4080, which has GDDR6X memory at 23 Gbps, this would be a significant jump which will in turn increase the total bandwidth from the memory from the maximum of 736 GB/s, up to 1 TB/s in the new RTX 5080, thanks to a 256-bit wide bus interface on the new card.
The full spec sheet for the 50 series of cards has yet to be confirmed, with rumours suggesting that the RTX 5090 will go up to 32 GB of GDDR7 memory (up from 24 GB of GDDR6X memory in the RTX 4090), this doesn"t come free however, with power draw increasing to 600w from 450w at the same time.
Graphics Card Name | NVIDIA GeForce RTX 5090 | NVIDIA GeForce RTX 5080 | NVIDIA GeForce RTX 4090 | NVIDIA GeForce RTX 4080 |
GPU Name | Blackwell GB202-300 | Blackwell GB203-400 | Ada Lovelace AD102-300 | Ada Lovelace AD103-300 |
GPU SMs | 170 (192 Full) | 84 (84 Full) | 128 (144 Full) | 76 (80 Full) |
GPU Cores | 21760 (+33%) | 10752 (+11%) | 16384 | 9728 |
Clock Speeds | TBD | TBD | 2520 MHz | 2505 MHz |
L2 Cache | TBD | TBD | 72 MB | 64 MB |
Memory Capacity | 32 GB GDDR7 (+33%) | 16 GB GDDR7 (0%) | 24 GB GDDR6X | 16 GB GDDR6X |
Memory Bus | 512-bit (+33%) | 256-bit (0%) | 384-bit | 256-bit |
Memory Speed | 28-32 Gbps | 32 Gbps | 21 Gbps | 23 Gbps |
Bandwidth | 1792-2048 GB/s | 1024 GB/s | 1008 GB/s | 736 GB/s |
TBP | 600W (+33%) | 400W (+25%) | 450W | 320W |
Power Interface | 12V-2x6 (16-Pin) | 12V-2x6 (16-Pin) | 12VHPWR (16-Pin) | 12VHPWR (16-Pin) |
The new cards are expected to be revealed during the NVIDIA keynote at CES 2025, which will take place on 6th January 2025, at 18:30 PT (01:30 GMT; 21:30 ET). More information can be found about the keynote on the official CES website.
Source: WCCFtech