Latest about Nvidia Blackwell
RTX 5080 Super rumored with 24GB of memory — Same 10,752 CUDA cores as the vanilla variant with a 400W+ TGP
Nvidia reportedly has an RTX 5080 Super in the making that ups the memory capacity by 50% over the base model from 16GB to 24GB.
Watch Nvidia's Computex 2025 keynote right here
Keep an eye on the live stream below to see what Jensen Huang announces.
Nvidia's H20 follow-up in China won't be based on Hopper, says Jensen
Future AI accelerators for China will not use the Hopper architecture, as Jensen Huang hints at a potential switch to Blackwell.
Nvidia RTX 5060 is up to 25% faster than RTX 4060 with frame generation in new GPU preview
Nvidia has given select outlets a chance to preview the RTX 5060 using very strict benchmarking measures. In these tests, the RTX 5060 is 16%—25 % faster than the RTX 4060.
RTX Pro 6000 Blackwell tested, performs roughly 10-15% faster than a stock RTX 5090
Nvidia's latest RTX 6000 Pro has been benchmarked by two outlets. On average, the GPU is allegedly 10-15% quicker than a stock clocked RTX 5090.
Nvidia postpones SOCAMM technology
Reliability and supply chain issues have allegedly forced Nvidia to delay SOCAMM to next-gen parts.
AMD to split flagship AI GPUs into specialized lineups for AI and HPC
But there is a major catch.
Lenovo unveils compact GB10 AI workstation
Lenovo is releasing a tiny AI workstation powered by the Nvidia GB10 Grace Blackwell Superchip.
