Nvidia "Blackwell Ultra" GB300 GPU to include 288GB of HBM3e memory and draw 1,400W
There will also be improvements in connectivity, F4 performance, and other areas
AMD's poor software optimization is letting Nvidia maintain an iron grip over AI chips
Lower total cost of ownership can't overcome software shortcomings
Asus leaks reveal 12GB mobile RTX 5070 Ti and 8GB mobile 5070 with Arrow Lake CPUs
The entry-level RTX 5050 also receives 8GB of VRAM
Microsoft surges ahead in AI race with massive Nvidia chip acquisition
It has purchased nearly 500,000 Nvidia flagship processors this year
The big picture: Microsoft has purchased a staggering number of Nvidia's Hopper chips this year, far outpacing what its rivals have been able to procure. With Microsoft's significant lead and its deep ties to OpenAI, the company is well-positioned as tech giants vie for AI supremacy.
Nvidia unveils palm-sized AI supercomputer for $249
The Jetson Orin Nano Super Developer Kit boasts a 70% performance boost over the previous model
Neural rendering might be Nvidia's next AI trick on RTX 5000
Inno3D mentions new technology and other AI enhancements coming to CES
Is the Nvidia App hurting performance? Here's what you need to know
A quick setting change fixes it
Editor's take: The Nvidia App, which is replacing both Nvidia Control Panel and GeForce Experience, has been praised for its modern features – but it may come with a small caveat: a performance hit when using certain overlay features. While this issue has caused concern among PC gamers, the situation is more nuanced than it first appears.
Zotac confirms 32GB RTX 5090 is on the way, 16GB RTX 5070 Ti and 5060 Ti could follow
Almost every Blackwell GPU could come with GDDR7 VRAM
Nvidia teases RTX 5000 series with Hype Meter, GeForce Greats, and LAN 50 promotions
More engagement equals better prizes
Next-gen Nvidia GPU "Rubin" is ahead of schedule, uses 3nm manufacturing and HBM4
Availability now expected in the second half of 2025
Nvidia challenger Tenstorrent completes $700 million funding round backed by Jeff Bezos, other high-profile investors
CEO Jim Keller is a strong advocate of open source
Nvidia's RTX 2060 Was Never Fast Enough for Ray Tracing
We revisit the GeForce RTX 2060 and Nvidia's promise of ray tracing from its base GPU some 6 years ago. Did this $350 GPU deliver on its potential?
Two more AMD graphics cards join the Steam survey, as Team Red achieves record CPU share
Elsewhere, the RTX 4060 mobile is close to becoming the most popular GPU
Company takes pre-orders for AI workstations with eight RTX 5090 GPUs, priced over $52,000
With a $10,500 deposit
Nvidia's Fugatto AI sound model claims to transform audio production
The model can create sounds that have never been heard before
Tech companies race to build AI superclusters with 100,000+ GPUs in high-stakes competition
Engineering challenges aside, it's unclear whether these investments will pay off
Don't Buy a GPU Now: Wait for Next-Gen or Grab a Discount?
Wondering if now's the time to upgrade your GPU? With key announcements and next-gen GPUs just weeks away, waiting is the smarter strategy than jumping on holiday sales.
Nvidia nearly doubles AMD's R&D budget – Intel's spending dwarfs both, but struggles to compete
As the world's largest company, Apple also leads in R&D spending
The big picture: The competitive strength of hardware makers is often gauged by their research and development expenditure. However, an analysis of recent financial reports from various tech giants reveals that higher R&D spending does not always guarantee success. Intel's recent struggles and Nvidia's astronomical growth driven by the AI boom have broken conventional assumptions.
The RTX 5090 uses Nvidia's biggest die since the RTX 2080 Ti
The massive chip measures 744mm2
Stalker 2: Heart of Chornobyl GPU Benchmark
After 15 years, Stalker 2: Heart of Chornobyl finally brings the series back, delivering Unreal Engine 5 visuals and intense gameplay. We tested 31 GPUs across resolutions and settings---let's dive in!
Nvidia RTX 5070 Ti leaks hint at RTX 5080-like architecture, 300W power draw
8,960 CUDA cores and 300W, VRAM and clock speeds still unknown
Jensen Huang envisions 24/7 AI factories: "Just like we generate electricity, we're now going to be generating AI"
First, though, some challenges have to be addressed
Nvidia's stellar Q3 proves that the age of AI is in full steam
Nvidia continues to ride the AI wave
Apple's M4 Max beats RTX 4070 in Blender, but falls short of the RTX 4080 Super
Can the rumored M4 Ultra take on the RTX 4090?
Garbage truck driver rescues dumped 32-core Threadripper PC with RTX 2080 Ti
It only needed some cleaning, a new power supply, and new storage