Corsair's versatile new Hydro Series brackets allow for CPU and GPU cooling

By Gabe Carey Published November 10, 2015

On its website, Corsair announced that it would be releasing today a new pair of water blocks capable of converting any Corsair Hyrdro Series CPU cooler into a convenient GPU cooler, supporting Nvidia’s GeForce GTX 980 Ti, Titan X, GTX 980, and GTX 970, among others.

Dubbed the HG10 N980 and HG10 N970, these new cooling brackets can work in conjunction with any liquid CPU cooler in the Corsair Hydro series. How it works is pretty simple: it converts the closed-loop system into a thermal GPU solution. As a result, if you’re into overclocking, this should presumably help you do so with ease.

Recommended Videos

Regardless of which bracket you choose, both come packed with a 70mm low-noise blower fan built in. The shroud on the N980 in particular is compatible with the stock PCB layouts of Nvidia’s GeForce GTX 980 Ti, 980, and Titan X cards. A multi-tasker, the cooling bracket is designed to refrigerate both the memory and voltage regulator modules (VRMs) of the graphics unit. The equally affordable N970, on the other hand, only chills the VRMs and is compatible exclusively with Nvidia’s GTX 970-flavored cards.

Please enable Javascript to view this content

Corsair has composed a complete list of graphics cards that can be used with the N980 and N870 liquid cooling brackets. In the tech specs section of each respective product page, Corsair ensures to mention popular GPU brands like MSI, Gigabyte, Galax, EVGA, Zotac, and PNY, along with specific model numbers for each brand. The N980, for instance, is compatible with four different models of the GTX 970, while the N970 can be used to cool several different models of the GTX 760, 670, and 660 Ti GPUs.

You can purchase both the Corsair Hydro HG10 N980 and the N970 from the company’s select set of authorized retailers or, alternatively, directly from its website. Both cooling brackets are priced moderately at $50 while a compatible CPU cooler can be purchased separately.

Topics

Former Digital Trends Contributor

A freelancer for Digital Trends, Gabe Carey has been covering the intersection of video games and technology since he was 16…

Computing

This AMD-powered Zhic gaming PC is on sale for less than $500

The Zhic 1 gaming PC on a white background.

Is it possible to get a solid gaming desktop for less than $500? With the discounts from gaming PC deals, you sure can. Here's a great example: the Zhic 1 gaming PC is available from Walmart for only $489, following a $110 discount on its original price of $599. It's tagged on the platform as a best seller, which means there's a chance that stocks of the machine are already running low. If you don't want to miss out on this offer, you're going to have to complete your transaction for this gaming desktop as soon as you can.

Why you should buy the Zhic 1 gaming PC
The Zhic 1 gaming PC is relatively affordable, so you shouldn't expect it to match up to the top-of-the-line models of the best gaming PCs. It's going to be more than enough to run the best PC games though, as it's equipped with the AMD Ryzen 5 5600G processor, AMD Radeon Vega Graphics, and 16GB of RAM that's the best place to start for gaming, according to our guide on how much RAM do you need. The Zhic 1 gaming PC features a removable cover, which would make it easy to upgrade its components in the future.

Computing

The Dell XPS 16 laptop with 32GB of RAM is $600 off — hurry!

The open Dell XPS 16 on a table.

There's always high demand for Dell XPS deals because everyone wants to get the stylish and powerful laptop for a lower price than usual. That's why we think time is already running out on this offer from Dell for the Dell XPS 16 -- a $600 discount on this configuration that usually sells for $3,050, for a lowered price of $2,450. You better hurry if you want to pocket the savings, as there's a chance the stocks up for sale will already be gone by tomorrow.

Why you should buy the Dell XPS 16
The Dell XPS 16, which is now the largest model in the popular series of laptops following the Dell XPS reset early last year, received a rating of 3.5 stars out of 5 in our review. We described it as "one of the most beautiful and powerful laptops you can buy," and it all begins with its attractive and ultramodern aesthetic that houses a 16.3-inch OLED touchscreen with UHD+ resolution. The display is paired with four speakers -- wo upward-firing tweeters and two side-firing woofers -- that provide amazing volume, clear mids and highs, and legitimate bass, perfect for listening to your favorite playlists and watching streaming shows.

Computing

I tested the future of AI image generation. It’s astoundingly fast.

Imagery generated by HART.

One of the core problems with AI is the notoriously high power and computing demand, especially for tasks such as media generation. On mobile phones, when it comes to running natively, only a handful of pricey devices with powerful silicon can run the feature suite. Even when implemented at scale on cloud, it’s a pricey affair.
Nvidia may have quietly addressed that challenge in partnership with the folks over at the Massachusetts Institute of Technology and Tsinghua University. The team created a hybrid AI image generation tool called HART (hybrid autoregressive transformer) that essentially combines two of the most widely used AI image creation techniques. th result is a blazing fast tool with dramatically lower compute requirement.
Just to give you an idea of just how fast it is, I asked it to create an image of a parrot playing a bass guitar. It returned with the following picture in just about a second. I could barely even follow the progress bar. When I pushed the same prompt before Google’s Imagen 3 model in Gemini, it took roughly 9-10 seconds on a 200 Mbps internet connection.

A massive breakthrough
When AI images first started making waves, the diffusion technique was behind it all, powering products such as OpenAI’s Dall-E image generator, Google’s Imagen, and Stable Diffusion. This method can produce images with an extremely high level of detail. However, it is a multi-step approach to creating AI images, and as a result, it is slow and computationally expensive.
The second approach that has recently gained popularity is auto-regressive models, which essentially work in the same fashion as chatbots and generate images using a pixel prediction technique. It is faster, but also a more error-prone method of creating images using AI.
On-device demo for HART: Efficient Visual Generation with Hybrid Autoregressive Transformer
The team at MIT fused both methods into a single package called HART. It relies on an autoregression model to predict compressed image assets as a discrete token, while a small diffusion model handles the rest to compensate for the quality loss. The overall approach reduces the number of steps involved from over two dozen to eight steps.
The experts behind HART claim that it can “generate images that match or exceed the quality of state-of-the-art diffusion models, but do so about nine times faster.” HART combines an autoregressive model with a 700 million parameter range and a small diffusion model that can handle 37 million parameters.