The mining performance of NVIDIA’s fastest graphics card, the GeForce RTX 3090 has leaked out. Spotted by I_Leak_VN over at Facebook, the mining performance was measured in the Ethereum mining algorithm where the chip scored a seriously impressive performance output but that alone does not make the card that good of a deal for miners.
NVIDIA’s GeForce RTX 3090 Delivers Impressive ETH Mining Performance, Up To 122 MH/s
There are reports of a resurgence in the mining segment which might cause inflated prices and lower stock for upcoming graphics cards so the leaked benchmarks might not come out as great news for all the consumers waiting to get hands-on new graphics cards. This is mainly because if mining does kick-off, then crypto miners are going to flock the market to get whatever GPU they can get their hands on hence causing even further stock outage of the RTX 3080 & RTX 3090 cards than the one we saw at launch day.
As for the mining performance itself, the GeForce RTX 3090 has a mining rate of up to 122 MH/s out of the box in Ethereum. The performance is based on stock numbers for the card which still makes it almost 49% faster than the GeForce RTX 3080 results we got to see a week back. The RTX 3080 scored around 82-84 MH/s at stock and up to 92-93 MH/s when overclocked.
The leaker doesn’t state which mining algorithm was he running for Ethereum. The previous one for the GeForce RTX 3080 was using the DaggerHashimoto algorithm so if the RTX 3090 results are based on a different algorithm, then the comparisons are useless.
While the card boasts some impressive mining performance, it should be noted that there are certain factors due to which it might not be a good buy for miners. First of all, is the price which being $1500 US doesn’t make for a great perf/$ value in the mining segment. Second is the huge power consumption which can be reverted by undervolting the card via software tweaks which would yield almost similar performance for higher power savings but even then, the cost and wattage don’t add up to a very sensible range.
NVIDIA GeForce RTX 3090 Graphics Card Specifications
The RTX 3090 features some insane specifications such as 82 SM units which results in a total of 10496 CUDA cores. In addition to the CUDA cores, the card also comes packed with next-gen RT (Ray-Tracing) cores, Tensor cores, and brand new SM or streaming multi-processor units. The card has a base clock of 1400 MHz and a boost clock of 1700 MHz with a TDP of 350W.
In terms of memory, the NVIDIA GeForce RTX 3080 comes packed with 24 GB of memory and that too the next-generation GDDR6X design. With Micron’s latest and greatest graphics memory dies, the RTX 3080 can deliver GDDR6X memory speeds of 19.5 Gbps. That along with a bus interface of 384-bit will deliver a cumulative bandwidth of 936 Gbps.
NVIDIA GeForce RTX 30 Series ‘Ampere’ Graphics Card Specifications:
|Graphics Card Name||NVIDIA GeForce RTX 3060 Ti||NVIDIA GeForce RTX 3070||NVIDIA GeForce RTX 3080||NVIDIA GeForce RTX 3090|
|GPU Name||Ampere GA104-200||Ampere GA104-300||Ampere GA102-200||Ampere GA102-300|
|Process Node||Samsung 8nm||Samsung 8nm||Samsung 8nm||Samsung 8nm|
|Transistors||17.4 Billion||17.4 Billion||28 Billion||28 Billion|
|TMUs / ROPs||TBA||TBA||272 / 96||TBA|
|Tensor / RT Cores||152 / 38||184 / 46||272 / 68||328 / 82|
|Base Clock||TBA||1500 MHz||1440 MHz||1400 MHz|
|Boost Clock||TBA||1730 MHz||1710 MHz||1700 MHz|
|FP32 Compute||TBA||20 TFLOPs||30 TFLOPs||36 TFLOPs|
|RT TFLOPs||TBA||40 TFLOPs||58 TFLOPs||69 TFLOPs|
|Tensor-TOPs||TBA||163 TOPs||238 TOPs||285 TOPs|
|Memory Capacity||8 GB GDDR6||8/16 GB GDDR6||10/20 GB GDDR6X||24 GB GDDR6X|
|Memory Speed||14 Gbps||14 Gbps||19 Gbps||19.5 Gbps|
|Bandwidth||448 Gbps||448 Gbps||760 Gbps||936 Gbps|