1. Introduction2. Gigabyte RTX 5080 Gaming OC3. MSI RTX 5080 Suprim SOC4. Palit RTX 5080 GamingPro OC5. Testing Methodology6. Game Benchmarks7. Clock Speed8. GPU Temperatures9. Acoustics10. Noise-Normalised Temperatures11. Power Draw and Efficiency12. Overclocking13. Closing Thoughts14. View All Pages

Today we are looking at no less than three RTX 5080 partner cards. We have the Gigabyte Gaming OC, MSI Suprim SOC, and the Palit GamingPro OC. With prices ranging from £1115 up to an eye-watering £1380, we put these three cards through their paces, looking at gaming performance, thermals, noise levels, power draw and more to see how they compare…

Timestamps

00:00 Intro
01:18 Gigabyte Gaming OC design
02:53 Gaming OC PCB + heatsink
03:46 MSI Suprim SOC design
05:15 Suprim SOC PCB + heatsink
06:05 Palit GamingPro OC design
07:27 GamingPro OC PCB + heatsink
07:44 Test setup
08:12 Thermals
08:46 Gigabyte thermal putty re-assembly testing
09:45 Noise and noise-normalised thermals
10:58 Gaming benchmarks, clock speed
12:17 Overclocking
13:38 Closing thoughts and pricing discussion

Following on from our launch day RTX 5080 review, today we are assessing the three partner cards we were sent for review. The MSI RTX 5080 Suprim SOC is undoubtedly the most premium of the bunch, priced at nearly £1400, while it uses the same cooler and heatsink design as we found on the RTX 5090 model, so we're expecting good things when it comes to thermal performance.

The Gigabyte RTX 5080 Gaming OC isn't quite so expensive at £1250, but is still designed to offer a suitably high-end experience, while Palit's RTX 5080 GamingPro OC is the cheapest of the bunch, but still very expensive at £1115. Lets find out exactly how each of these cards perform.

	RTX 5090	RTX 5080	RTX 4090	RTX 4080 Super	RTX 4080
Process	TSMC N4	TSMC N4	TSMC N4	TSMC N4	TSMC N4
SMs	170	84	128	80	76
CUDA Cores	21760	10752	16384	10240	9728
Tensor Cores	680	336	512	320	304
RT Cores	170	84	128	80	76
Texture Units	680	336	512	320	304
ROPs	176	112	176	112	112
GPU Boost Clock	2407 MHz	2617 MHz	2520 MHz	2550 MHz	2505 MHz
Memory Data Rate	28 Gbps	30 Gbps	21 Gbps	23 Gbps	22.4 Gbps
L2 Cache	98304 KB	65536 KB	73729 KB	65536 KB	65536 KB
Total Video Memory	32GB GDDR7	16GB GDDR7	24GB GDDR6X	16GB GDDR6X	16GB GDDR6X
Memory Interface	512-bit	256-bit	384-bit	256-bit	256-bit
Memory Bandwidth	1792 GB/Sec	960 GB/Sec	1008 GB/Sec	736 GB/Sec	716.8 GB/Sec
TGP	575W	360W	450W	320W	320W

First, a quick spec recap. Unlike the RTX 5090, which is built on the GB202 die, RTX 5080 uses smaller silicon as it is a full implementation of the GB203 die, measuring 378mm². Comprised of 7 Graphics Processing Clusters (GPCs), each holds up to eight Texture Processing Clusters (TPCs), with a total of 42. Each TPC is home to two Streaming Multiprocessors (SMs), giving us 84, and each SM still holds 128 CUDA Cores, meaning the RTX 5080 has a total of 10752 shaders. We also find 84 RT cores, 336 Tensor cores, 336 Texture Units, and 112 ROPs.

This time around, however, there's no node-shrink, and GB203 remains fabricated on TSMC's N4 node, as per the RTX 40-series. As such, rated clock speed is barely changed this generation, with the RTX 5080 rated at 2617MHz, compared to the RTX 4080 Super's 2550MHz boost.

The memory configuration is also fairly similar, but sports one key upgrade – GDDR7 memory. The RTX 5080 comes equipped with 16GB, running at 30Gbps, and that puts total memory bandwidth at 960 GB/s, a 30% increase over the RTX 4080 Super. L2 cache remains at 65MB.

Power draw has also increased, with the RTX 5080 sporting a 360W TGP. This is something we focus on closely in this review, using our enhanced GPU power testing methodology, so read on for our most detailed power and efficiency testing yet.

Become a Patron!