Latest about GPUs
Nvidia announces Rubin GPUs in 2026, Rubin Ultra in 2027, Feynman also added to roadmap
NVL144 and NVL576 configurations coming down the pipe.
Nvidia announces Blackwell Ultra B300 —1.5X faster than B200 with 288GB HBM3e and 15 PFLOPS dense FP4
Nvidia officially revealed its Blackwell Ultra B300 data center GPU, which packs up to 288GB of HBM3e memory and offers 1.5X the compute potential of the existing B200 solution.
AMD RX Vega 64 runs Indiana Jones and the Great Circle at well over 30FPS in Linux with RADV driver
RADV features baked-in ray-tracing software emulation, enabling ray-tracing functionality on AMD GPUs dating back to first-generation GCN GPUs.
Intel finally releases the XeSS 2.0 SDK for developers — Technology still gated by closed-source barriers
The XeSS SDK 2.0.1 is now available, bringing support for XeSS-SR, XeSS-FG, and XeLL, though the technology itself remains closed-source.
The GPU benchmarks hierarchy 2025
We've run hundreds of GPU benchmarks on Nvidia, AMD, and Intel graphics cards and ranked them in our comprehensive hierarchy, with over 80 GPUs tested.
GPU Price Index 2025: Lowest Nvidia, AMD, and Intel prices
Check the best prices on Nvidia RTX and AMD Radeon graphics cards.
MSI Afterburner update enables RTX 50 series owners to push their GDDR7 VRAM up to 36 GT/s
An unofficial MSI Afterburner update by Unwinder unlocks memory overclocking for Nvidia's GeForce RTX 50-series graphics cards.
AMD manager reports 45% GPU retail market share in Japan — Eyes 70% as the next target
AMD marketing manager Yoshiaki Sato reported that Radeon GPUs have accounted for 45% of GPU sales in Japan, presumably since RDNA 4 launched.
