NVIDIA GeForce GTX 1080 Ti vs NVIDIA GeForce RTX 5090 D V2 Comparison

NVIDIA
GEFORCE

NVIDIA GeForce GTX 1080 Ti

CORE STATE GP102
VRAM 11 GB
CLOCK SPEED 1582 MHz
TDP 250 W
BUS WIDTH 352 bit
ARCHITECTURE Pascal
nm
PROCESS 16 nm
LAUNCH DATE 2017
VS
NVIDIA
GEFORCE

GeForce RTX 5090 D V2

CORE STATE GB202
VRAM 24 GB
CLOCK SPEED 2407 MHz
TDP 575 W
BUS WIDTH 384 bit
ARCHITECTURE Blackwell 2.0
nm
PROCESS 5 nm
LAUNCH DATE 2025

PERFORMANCE BENCHMARKS

3dmark_3dmark_steel_nomad_dx12
2,231
16,504
geekbench_metal
30,624
N/A
geekbench_opencl
67,929
N/A
geekbench_vulkan
40,511
N/A
passmark_directx_10
118
N/A
passmark_directx_11
151
N/A
passmark_directx_12
66
N/A
passmark_directx_9
231
N/A
passmark_g2d
939
N/A
passmark_g3d
18,600
N/A
passmark_gpu_compute
9,632
N/A

Analysis: NVIDIA GeForce GTX 1080 Ti vs NVIDIA GeForce RTX 5090 D V2

# NVIDIA GeForce RTX 5090 D V2 vs NVIDIA GeForce GTX 1080 Ti

The benchmark chasm between these two NVIDIA generations is almost absurd. In the single shared test, 3DMark Steel Nomad DX12, the RTX 5090 D V2 scores 16504 against the GTX 1080 Ti’s 2231, a 639.8% difference. That is not an incremental upgrade; it is a seismic shift in compute capability. Interestingly, despite this massive raw performance gap, both cards sit within one percentile point of each other globally — the RTX 5090 D V2 at the 59th percentile and the GTX 1080 Ti at the 58th. This suggests that percentile rankings are heavily weighted by the broader benchmark suite, which the older card has more results for, rather than pure peak performance. The data reveals a story of two very different eras, separated by eight years and a complete architectural revolution.

Head-to-Head Benchmarks

The only direct head-to-head result in the dataset is 3DMark Steel Nomad DX12, and it is a landslide. The RTX 5090 D V2 posts 16504 points, while the GTX 1080 Ti manages just 2231. The deltaPct of 639.8% means the newer card is roughly 7.4 times faster in this specific workload. Steel Nomad is a modern DX12 test designed to stress current-generation hardware, so the result is expected, but the magnitude still shocks. For context, the RTX 5090 D V2’s nearest rivals in the aggregate database are the NVIDIA T400 (16508, 0% delta) and AMD Radeon PRO W7500 (16415, 0.5% delta). The GTX 1080 Ti’s nearest rivals are the AMD Radeon R9 M380 (15521, 0.2% delta) and AMD Radeon Pro W5500 (15679, -0.8% delta). This placement is telling: the modern card trades blows with professional workstation GPUs, while the Pascal flagship now sits alongside entry-level mobile and mid-range workstation parts.

The GTX 1080 Ti does have additional benchmark results that the RTX 5090 D V2 lacks, including Geekbench Metal (30624), OpenCL (67929), and Vulkan (40511), plus a series of Passmark tests. However, these cannot be compared directly since no corresponding scores exist for the newer card. The Passmark G3D score of 18600 and GPU compute score of 9632 give a sense of the older card’s legacy performance, but without equivalent data for the RTX 5090 D V2, these numbers stand alone. What the data does show is that the GTX 1080 Ti, despite its age, still holds a respectable aggregate average of 15548, which is only 5.8% below the RTX 5090 D V2’s single benchmark score of 16504 — but that aggregate includes many older, less demanding tests where the Pascal card can still compete.

FAQ

Q: How much faster is the RTX 5090 D V2 in the shared benchmark?

A: The RTX 5090 D V2 scores 16504 in 3DMark Steel Nomad DX12, versus 2231 for the GTX 1080 Ti, a delta of 639.8% in favor of the newer card.

Q: Do both cards have ray tracing and tensor cores?

A: No. The RTX 5090 D V2 includes 170 RT cores and 680 tensor cores, while the GTX 1080 Ti lists null values for both, meaning it has neither dedicated hardware.

Q: What is the memory configuration difference?

A: The RTX 5090 D V2 has 24 GB of GDDR7 on a 384-bit bus with 1.34 TB/s bandwidth. The GTX 1080 Ti has 11 GB of GDDR5X on a 352-bit bus with 484.4 GB/s bandwidth.

Q: Which card is still in production?

A: The RTX 5090 D V2 has an "Active" production status, released on 2025-08-14. The GTX 1080 Ti is "End-of-life," released on 2017-03-09.

Q: How do their transistor counts compare?

A: The RTX 5090 D V2 packs 92,200 million transistors on a 5 nm TSMC process. The GTX 1080 Ti has 11,800 million transistors on a 16 nm TSMC process.

Q: What is the API support difference?

A: Both support OpenGL 4.6 and Vulkan 1.4, but the RTX 5090 D V2 supports DirectX 12 Ultimate (12_2), while the GTX 1080 Ti is limited to DirectX 12 (12_1).

Architecture Differences

The architectural gulf between Blackwell 2.0 and Pascal is the core story. The RTX 5090 D V2 uses the GB202 chip, built on a 5 nm TSMC process, while the GTX 1080 Ti uses the GP102 chip on 16 nm TSMC. That process shrink alone allows the newer card to house 92,200 million transistors versus 11,800 million — a 7.8x increase — on a die that is 750 mm² versus 471 mm². The transistor density tells the tale: 122.9 million transistors per mm² for Blackwell 2.0 against just 25.1 million for Pascal. This is not just more of the same; it is a fundamentally different approach to computing.

The RTX 5090 D V2 introduces dedicated RT cores (170) and tensor cores (680), which the GTX 1080 Ti completely lacks. This means hardware-accelerated ray tracing and AI-accelerated workloads are simply unavailable on the Pascal card. The shading unit count also explodes: 21760 on the newer card versus 3584 on the older one. Texture mapping units jump from 224 to 680, and ROPs from 88 to 176. The FP32 compute rating of 104.8 TFLOPS on the RTX 5090 D V2 dwarfs the GTX 1080 Ti’s 11.34 TFLOPS — a 9.2x difference. Even FP16 performance is stark: the newer card delivers 104.8 TFLOPS (1:1 ratio), while the older one manages 177.2 GFLOPS (1:64 ratio), meaning the RTX 5090 D V2 is roughly 591x faster in half-precision compute. This is not an evolution; it is a complete redesign.

Specification Differences

The memory subsystem is a major differentiator. The RTX 5090 D V2 offers 24 GB of GDDR7 across a 384-bit bus, achieving 1.34 TB/s bandwidth. The GTX 1080 Ti has 11 GB of GDDR5X on a 352-bit bus, with 484.4 GB/s bandwidth. That is more than 2.7x the bandwidth in favor of the newer card, alongside more than double the capacity. Clock speeds tell a nuanced story: the RTX 5090 D V2 has a base clock of 2017 MHz and boost of 2407 MHz, while the GTX 1080 Ti runs at 1481 MHz base and 1582 MHz boost. The newer card’s memory clocks at 1750 MHz (28 Gbps effective), versus 1376 MHz (11 Gbps effective) for the older card.

Power and connectivity also diverge sharply. The RTX 5090 D V2 draws a 575 W TDP with a recommended 950 W PSU, using a single 16-pin connector. The GTX 1080 Ti requires 250 W TDP and a 600 W PSU, using one 6-pin and one 8-pin connector. The bus interface moves from PCIe 3.0 x16 to PCIe 5.0 x16. Display outputs upgrade from 1x HDMI 2.0 and 3x DisplayPort 1.4a to 1x HDMI 2.1b and 3x DisplayPort 2.1b. Physical dimensions also grow: the RTX 5090 D V2 measures 304 mm x 137 mm x 48 mm, while the GTX 1080 Ti is 267 mm x 112 mm x 40 mm. Both are dual-slot cards, but the newer one is substantially larger in every dimension.

Where Each One Wins

The RTX 5090 D V2 wins in every conceivable performance metric from the data. In the single head-to-head test, it is 639.8% faster. Its memory bandwidth of 1.34 TB/s enables workloads that the GTX 1080 Ti’s 484.4 GB/s simply cannot handle. The 24 GB frame buffer versus 11 GB means larger textures, higher resolutions, and more complex scenes are feasible. The presence of RT cores and tensor cores opens up ray tracing and AI features that are entirely absent on the Pascal card. The FP32 throughput of 104.8 TFLOPS versus 11.34 TFLOPS makes the newer card suitable for compute-heavy tasks like scientific simulation or deep learning inference, where the older card would be a bottleneck.

The GTX 1080 Ti’s wins are more subtle and derived from its broader benchmark portfolio. Its Passmark G3D score of 18600 and GPU compute score of 9632 demonstrate that, in legacy DX10, DX11, and DX9 workloads, it still performs admirably. The Geekbench Vulkan score of 40511 shows it can handle modern APIs competently, even without dedicated RT hardware. Its 250 W TDP and 600 W PSU requirement make it far easier to integrate into existing systems without upgrading power delivery. The smaller physical footprint (267 mm vs 304 mm length) means it fits in more compact cases. For users on older platforms with PCIe 3.0, the card is a drop-in solution, whereas the RTX 5090 D V2’s PCIe 5.0 interface is forward-looking but may not offer full benefit on legacy motherboards.

The Verdict

The data is unambiguous: the RTX 5090 D V2 is the superior card in nearly every measurable way. Its 639.8% lead in 3DMark Steel Nomad DX12, combined with 24 GB of GDDR7 memory, 104.8 TFLOPS FP32, and dedicated RT and tensor cores, makes it the clear choice for anyone needing maximum performance in modern DX12 workloads, ray tracing, or AI-accelerated tasks. The 59th percentile ranking, despite the massive score, suggests that the benchmark database includes many professional and server GPUs that skew the distribution, but within consumer gaming hardware, this card is near the top.

The GTX 1080 Ti, however, still has a role. Its 58th percentile ranking, nearly identical to the newer card, indicates that its aggregate performance across a wide range of tests is still respectable. For users running legacy applications that rely on DX10, DX11, or DX9, the Pascal card’s Passmark scores (118, 151, and 231 respectively) show it handles these workloads without issue. Its 250 W TDP and 600 W PSU requirement make it a practical choice for budget-conscious system builders who do not need current-generation features. The launch MSRP of 699 USD for the GTX 1080 Ti, compared to 2,299 USD for the RTX 5090 D V2, reflects the enormous performance delta — though the newer card’s price is not discussed further here.

Ultimately, the choice depends on workload. For modern gaming, content creation, or compute tasks, the RTX 5090 D V2 is the only rational option from this data. For retro gaming, legacy software compatibility, or low-power builds, the GTX 1080 Ti remains a functional, if dated, choice. The architecture gap is not just about speed; it is about capability. The RTX 5090 D V2 can do things the GTX 1080 Ti physically cannot, and no amount of driver optimization can bridge that divide.

DETAILED SPECIFICATIONS

SPECIFICATION
GTX 1080 Ti
RTX 5090 D V2
Core Specs
Shading Units
3,584
21,760 +507.1%
Shaders
3,584
21,760 +507.1%
TMUs
224
680 +203.6%
ROPs
88
176 +100.0%
SM Count
28
170 +507.1%
Clocks
Base Clock
1481 MHz
2017 MHz
Boost Clock
1582 MHz
2407 MHz
Memory Clock
1376 MHz 11 Gbps effective
1750 MHz 28 Gbps effective
Memory
Memory Size
11 GB
24 GB
VRAM (MB)
11,264
24,576 +118.2%
Memory Type
GDDR5X
GDDR7
Memory Bus
352 bit
384 bit
Bandwidth
484.4 GB/s
1.34 TB/s
Cache
L1 Cache
48 KB (per SM)
128 KB (per SM)
L2 Cache
2.75 MB
96 MB
Performance
Pixel Rate
139.2 GPixel/s
423.6 GPixel/s
Texture Rate
354.4 GTexel/s
1,636.8 GTexel/s
FP32 (TFLOPS)
11.34 TFLOPS
104.8 TFLOPS
FP64 (TFLOPS)
354.4 GFLOPS (1:32)
1.637 TFLOPS (1:64)
FP16 (TFLOPS)
177.2 GFLOPS (1:64)
104.8 TFLOPS (1:1)
AI/RT
RT Cores
—
170
Tensor Cores
—
680
Power
TDP
250 W
575 W
TDP (W)
250
575 +130.0%
Suggested PSU
600 W
950 W
Power Connectors
1x 6-pin + 1x 8-pin
1x 16-pin
Architecture
Architecture
Pascal
Blackwell 2.0
GPU Name
GP102
GB202
Generation
GeForce 10
GeForce 50
Process Size
16 nm
5 nm
Transistors
11,800 million
92,200 million
Die Size
471 mm²
750 mm²
Foundry
TSMC
TSMC
Density
25.1M / mm²
122.9M / mm²
API Support
DirectX
12 (12_1)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
3.0
3.0
CUDA
6.1
12.0
Shader Model
6.8
6.9
Physical
Slot Width
Dual-slot
Dual-slot
Length
267 mm 10.5 inches
304 mm 12 inches
Height
112 mm 4.4 inches
137 mm 5.4 inches
Outputs
1x HDMI 2.03x DisplayPort 1.4a
1x HDMI 2.1b3x DisplayPort 2.1b
Bus Interface
PCIe 3.0 x16
PCIe 5.0 x16
Other
Launch Price
699 USD
2,299 USD
Production
End-of-life
Active
Predecessor
GeForce 900
GeForce 40
Successor
GeForce 20
GeForce 60
View GeForce GTX 1080 Ti Details View GeForce RTX 5090 D V2 Details