"NVIDIA" content on TweakTown - Page 5
We found 8535 items for the tag: NVIDIA
MAINGEAR's new ZERO desktop PC with hidden motherboard cables is now available, starts at $1399
MAINGEAR's sleek new ZERO desktop gaming PC is now available starting from $1399, featuring MSI's new Project Zero motherboards and cases.
SK hynix was the initial exclusive supplier of HBM3 to NVIDIA, Samsung and Micron catching up
Samsung will have its HBM inside of NVIDIA's upcoming H200 AI GPU, also receiving certification for AMD's new Instinct MI300 AI GPU.
NVIDIA projected to make $130 billion from AI GPUs in 2026, which is 5x higher than 2023
NVIDIA revenue expected to grow to a huge $130 billion in 2026 thanks to the future of AI GPUs, which the company absolutely dominates.
Meta has two new AI data centers equipped with over 24,000 NVIDIA H100 GPUs
By the end of 2024, Meta plans to have 350,000 NVIDIA H100 GPUs powering its AI infrastructure - it's all part of its 'ambitious' AI roadmap.
AMD Ryzen 9 7950X used by cryptominers, making $3 per day in profit from their CPUs
AMD's current-gen Ryzen 9 7950X processor is using used for cryptomining, as it's more profitable than GPU mining while Bitcoin rides new highs.
Samsung to use MR-MUF technology, like SK hynix, for its future-gen HBM products
Samsung to address HBM yield issues by using MUF technique, which SK hynix pioneered, moving away from its NCF technology for HBM products.
Sycom's Silent Master GeForce RTX 4070 Ti SUPER uses Noctua Fans and it's 3.8 slots thick
A GPU with Noctua fans is a surefire way to lower the noise generated while gaming, but it's also a surefire way to turn any GPU into a thick boy.
GeForce RTX 40 SUPER Series GPU pricing falls below MSRP in Germany
It's only been a month or two since they first hit the scene, but the new GeForce RTX 40 SUPER cards are now being sold in Germany at prices below MSRP.
JEDEC chills on next-gen HBM4 thickness: 16-Hi stacks with current bonding tech allowed
JEDEC has reportedly eased HBM4 memory configurations to help HBM manufacturers, reducing thickness of HBM4 to 775 micrometers for 12-layer, 16-layer HBM4.
Cerebras WSE-3 wafer-scale AI chip: 57x bigger than largest GPU with 4 trillion transistors
Cerebras Systems unveils its new WSE-3 AI chip that's 57x larger than NVIDIA H100 AI GPU, with 4 trillion transistors, and 900,000 AI-optimized cores.
'Most' Nintendo Switch 2 games will use NVIDIA DLSS and Nintendo passed on using Lovelace
According to rumors, Nintendo Switch 2 game developers will have the option to enable NVIDIA DLSS, it won't be mandatory. Also, Nintendo said no to Ada.
Micron HBM3E for NVIDIA's beefed-up H200 AI GPU has shocked HBM competitors like SK hynix
Micron partnering with NVIDIA for its upcoming H200 AI GPU with upgraded HBM3E memory has HBM competitors like SK hynix and other 'shocked'.
AIDA64 v7.20 released, benchmark tool adds Dark Mode and support for GeForce RTX 40 SUPER GPUs
AIDA64 v7.20 has been released, with the popular system information and benchmark tool finally getting a feature we've been waiting for.
AMD's Ryzen 8000G with integrated Radeon graphics outperforms China's Moore Threads MTT S80 GPU
Even after driver updates the Chinese-made Moore Threads MTT S80 GPU fails to match the performance of AMD's Ryzen APU line-up with integrated graphics.
The legendary GeForce GTX 1080 Ti is celebrating its 7th anniversary this week
Seven years in the tech world is akin to ancient history, and this week we celebrate the launch of iconic GeForce GTX 1080 Ti back in 2017.
DirectX 12 'Work Graphs' aim to eliminate CPU bottlenecks by putting the GPU in charge
Microsoft's big update for DirectX and PC game development aims to eliminate CPU bottlenecks and improve performance with GPU-driven rendering.
NVIDIA GeForce RTX 50 Series to use 28Gbps GDDR7 memory, 33% higher bandwidth than RTX 4090
We've now got more info on the next-gen GDDR7 memory that will power NVIDIA's next-gen GeForce RTX 'Blackwell' GPUs, slower than previously expected.
NVIDIA sued by three authors for copyright infringement
NVIDIA has been sued by three authors, who claim that the company used its books without their permission to train its AI platform, NeMo.
CPU real-time ray-tracing is here, but performance in Quake 2 RTX sits at 1 FPS
Real-time ray-tracing with just a CPU is possible with the latest Mesa CPU-based Vulkan driver, but performance is terrible without hardware acceleration.
AMD Radeon RX 7700 XT available for $399, same price as the RTX 4060 Ti it outperforms
With AMD recently dropping the price of its mid-range Radeon RX 7700 XT GPU to $419, you can now pick up the Sapphire PULSE model for as low as $399.
NVIDIA CEO Jensen Huang says next-gen DGX AI system will be liquid cooled
NVIDIA CEO Jensen Huang confirms next-gen DGX AI system will be liquid-cooled, off the back that Dell confirmed B200 will use up to 1000W of power.
NVIDIA GeForce RTX 50 series GPUs: same memory interface as RTX 40 series, with next-gen GDDR7
NVIDIA's next-gen GeForce RTX 50 series 'Blackwell' GPUs will use next-gen GDDR7 memory, with a 384-bit memory bus we'll see 1.5TB/sec memory bandwidth.
The TT Show Episode 25 - Next-Gen Switch, GeForce RTX, and Radeon Gaming!
This week... Nintendo Switch 2, GeForce RTX 5090, Radeon RX 8800 XT, Apple cancels its electric car, and Microsoft's Copilot AI thinks it's a god!
NVIDIA GeForce Now gets G-Sync and Reflex, so it's 'nearly indistinguishable' from a local PC
Or so NVIDIA claims anyway, and clearly, these two technologies are going to be of major benefit to subscribers signed up for the cloud gaming service.
SK hynix investing a further $1 billion to lead in HBM memory for future-gen AI GPUs
SK hynix says the first 50 years of the semiconductor industry was about the front-end, while the next 50 years are about the back end aka packaging.
The first-gen GDDR7-based graphics cards will use 16Gb dies, 2GB minimum, and 32Gbps speeds
The first generation of GPUs based on GDDR7 memory will use 16Gb dies and 2GB VRAM capacities, at 32Gbps bandwidth, says hardware leaker.
Analyst: NVIDIA is the 'kingmaker' with projected $87 billion in AI, data center GPUs in 2024
NVIDIA is the 'kingmaker' according to analyst firm Omdia, which predicts that NVIDIA will make $87 billion from data center GPUs in 2024 alone.
Samsung expected to unveil world's first HBM3e 12-High memory at NVIDIA GTC 2024
Samsung is expected to make 'groundbreaking reveal' at NVIDIA GTC 2024, where it will show off physical HBM3E 12-Hi memory for next-gen AI GPUs.
AMD now allows Ryzen AI CPUs and Radeon RX 7000 GPUs to run localized AI chatbots using LLMs
AMD details how to run a Large Language Model (LLM) AI-powered chatbot on your Ryzen AI PC or Radeon RX 7000 series GPU, you can try it out right now!
SK hynix reportedly supplied new 12-layer HBM3E memory samples to NVIDIA last month
SK hynix reportedly provided initial samples of its new 12-layer HBM3E memory to NVIDIA last month, offering 36GB HBM3E per stack.
Ghost of Tsushima Director's Cut launches DLSS3, FSR3, XeSS support on the PC on May 16
Ghost of Tsushima Director's Cut for the PC has been announced, launches on May 16: supports up to 48:9 aspect ratio, with AI-upscaling from everyone.
NVIDIA cuts price of RTX 4060 Ti (16GB) GPU after AMD pressure, but it's unlikely to be enough
Considering the relative merits of the freshly reduced RX 7700 XT and the RTX 4060 Ti 16GB, we don't feel the NVIDIA GPU is quite competitive enough yet.
End of an era, NVIDIA has produced its last GeForce GTX GPU... it's all RTX from here on out
NVIDIA has stopped making GeForce GTX 16 Series GPUs, retiring the 'GTX' branding while shifting its entry-level focus to cards like the RTX 3050 6GB.
Horizon Forbidden West PC specs revealed, playable with a GPU with only 4GB of VRAM
Horizon Forbidden West Complete Edition specs - GeForce RTX 3060 recommended for 1080p 60 FPS and GeForce RTX 3070 for 1440p 60 FPS without DLSS.
NVIDIA GeForce Game Ready Driver 551.76 is here, adds support for The Thaumaturge
NVIDIA GeForce Game Ready Driver 551.76 offers day one support for The Thaumaturge while fixing a couple of issues - one game related and one NVENC.
NVIDIA's new open-source Nouveau driver for Linux: no issues with HDMI 2.1, unlike AMD
NVIDIA's new open-source Linux graphics driver -- Nouveau -- won't have issues with HDMI 2.1 integration, meanwhile there's issues galore with AMD.
JEDEC publishes GDDR7 memory standard: AMD and NVIDIA's next-gen graphics memory is ready
JEDEC publishes the next-gen GDDR7 graphics memory standard: double the bandwidth of GDDR6, for the future of gaming and AI GPU hardware.
Alan Wake 2 patch improves performance by up to 100% on older GeForce GTX 10 Series GPUs
A 57% performance bump with the GeForce GTX 1070, 85% with the GTX 1080, and 100% with the GTX 1080 TI - Alan Wake 2's next patch is a game changer.
AMD's cut-down AI GPU for China market blocked by US government
AMD has been halted by the US Commerce Department, banning its AI processors from shipping to China, even though it was cut-down AI GPU.
TSMC plans huge recruitment drive with 6000 new jobs with higher salaries, job perks, and more
TSMC has launched its 2024 campus recruitment campaign, with 6000 jobs on offer with engineers and technicians highty sought after in Taiwan.
Meta switches from TSMC to Samsung Foundry for AI chips, 'uncertainty and volatility' at TSMC
Meta CEO Mark Zuckerberg has partnered with Samsung Foundry, reducing its reliance on TSMC: describing the current situation with TSMC as 'volatile'.
AMD teases next-gen AI upscaling technology, could use AI in new FSR to combat NVIDIA DLSS
AMD CTO Mark Papermaster teases that their gaming devices will use AI for upscaling in 2024, and that this year is a 'really huge development year'.
NVIDIA RTX 5090 could launch in Q3 2024 to crush AMD in the gaming GPU arena
Blackwell flagship graphics card should crack 4K resolution, 240Hz gaming, and it might even turn up before AMD releases its next-gen RDNA 4 GPUs.
GeForce RTX 4070 SUPER is already listed in Steam's hardware survey for February 2024
The GeForce RTX 4070 SUPER launched in January 2024 and is proving to be one of the most popular GPU launches of this current generation.
Samsung's next-gen 2nm-class production node will have backside power delivery, like Intel
Samsung reportedly looking at backside power delivery network with its upcoming SF2 process node in 2025, its upcoming 2nm-class manufacturing process.
MSI is reportedly prepping to launch another EXPERT GPU for the GeForce RTX 4070 Ti SUPER
The MSI GeForce RTX 4080 SUPER EXPERT is one of the more noteworthy 2024 GPU releases, and MSI is prepping to launch a RTX 4070 Ti SUPER EXPERT.
LG reveals full specs and pricing for its dual 4K 240 Hz and 1080p 480 Hz OLED gaming display
LG's new dual OLED display that offers 4K and 1080p modes with varying refresh rates is available now for pre-order for $1,399.99.
NVIDIA CEO Jensen Huang: AI should pass ANY human tests, exams in 5 years
NVIDIA CEO Jensen Huang asked on when AI computers will think like humans, he said AGI will arrive soon, should do every human test or exam in 5 years.
HP's new Omen Transcend 32-inch OLED monitor: on-board DisplayPort 2.1 is slower than HDMI 2.1
HP's new Omen Transcend 32-inch OLED gaming monitor features the latest DisplayPort 2.1 connectivity, can't do 4K 240FPS without using DSC.
NVIDIA's next-gen B200 AI GPU uses 1000W of power per GPU, drops in 2025, confirmed by Dell
NVIDIA's next-generation Blackwell B100 AI GPU launches this year, but Dell just confirmed the upgraded B200 AI GPU for 2025 with 1000W of power.