AMD Fury X Quadfire Results

/ 1 year ago


There’s been a lot of negative press about the new AMD cards recently, but there is a diamond in the rough to be found. Despite the poorer than expected, although still very impressive, performance of the Fury X, it didn’t stop AMD employee, Matt Buck in pursuing ultimate performance with not two, not three, but four of these beats in a CrossFireX configuration.

Now one alone is enough to handle 4K gaming with a few dips under 60FPS, two should sort you out to never see under 60FPS; four on the other hand, is enough to run a decent 12K Eyefinity set-up.

It’s all well and good buying and flaunting these graphics cards, but what we all want to see is how it fares in a benchmark. Thankfully, that has already been done in the form of 3DMark Firestrike Ultra (4K), along with single increments of each card. With the addition of each card, we see almost perfect scaling, losing only around 12% performance per card per addition





Looking at that result has got me thinking, even with one of the most power GPUs on the planet, surely only 4GB of VRAM proves a hindrance or is this the start of HBM where the increased bandwidth interprets more information and thus has lowered the VRAM requirement compared to GDDR5. Let us know your thoughts in the comments section.

UPDATE: Looking through some of Matt’s previous posts on forums, it seems he has posted a 4K QuadFire Fury benchmark using Thief. When compared to the 4K Quad SLI Titan X benchmark; the Fury combination pins the NVIDIA option by almost 5 FPS.

thief 4k fury

4K Thief Benchmark: Quadfire AMD FuryX

theif 4k titan

4K Thief Benchmark: Quad SLI NVIDIA Titan X

Topics: , , , , , , ,

  • Neil Mathieson

    Lucky guy gets to play with four of them at a time. Two would be ~my~ sweet spot.

  • zerocool


  • Quentin

    One of the users on (Baasha, I think) showed that 4x Titan X did not scale well at 5K; I wonder how the Fury X compares?