NVIDIA GeForce GT 545 vs NVIDIA GeForce RTX 5080 SUPER Comparison

NVIDIA
GEFORCE

NVIDIA GeForce GT 545

CORE STATE GF116
VRAM 1536 MB
CLOCK SPEED —
TDP 70 W
BUS WIDTH 192 bit
ARCHITECTURE Fermi 2.0
nm
PROCESS 40 nm
LAUNCH DATE 2011
VS
NVIDIA
GEFORCE

GeForce RTX 5080 SUPER

CORE STATE GB203
VRAM 24 GB
CLOCK SPEED 2617 MHz
TDP 415 W
BUS WIDTH 256 bit
ARCHITECTURE Blackwell 2.0
nm
PROCESS 5 nm
LAUNCH DATE 2026

PERFORMANCE BENCHMARKS

geekbench_opencl
3,594
N/A
3dmark_3dmark_steel_nomad_dx12
N/A
3,075

Analysis: NVIDIA GeForce GT 545 vs NVIDIA GeForce RTX 5080 SUPER

The NVIDIA GeForce RTX 5080 SUPER and the NVIDIA GeForce GT 545 represent two distinct eras of GPU design, separated by over a decade of architectural evolution. The data available for these cards is drawn from different benchmark suites—the RTX 5080 SUPER is measured via 3DMark Steel Nomad DX12, while the GT 545 is assessed through Geekbench OpenCL—making a direct apples-to-apples comparison impossible. However, the raw specifications and the contextual performance data from their nearest rivals provide a clear picture of their relative standing.

Head-to-Head Benchmarks

There is no overlapping benchmark data between the RTX 5080 SUPER and the GT 545, so a direct score-to-score comparison cannot be made. Instead, the data shows where each card sits within its own performance ecosystem. The RTX 5080 SUPER's sole benchmark result is a 3DMark Steel Nomad score of 3075, which places it at the 19th percentile of all GPUs. This is a surprisingly low percentile for a modern flagship, suggesting that while the card is capable, it is not at the top of the overall performance hierarchy. Its nearest rivals in this test include the NVIDIA Quadro P1000 (average score 3163, 2.8% higher), the Intel Arc Pro B60 (average score 3182, 3.4% higher), and the NVIDIA GeForce 820A (average score 2983, 3.1% lower). The RTX 5080 SUPER trails the Quadro P1000 and Arc Pro B60 by a narrow margin, while edging out the GeForce 820A by 3.1%.

On the other side, the GT 545 posts a Geekbench OpenCL score of 3594, placing it at the 21st percentile of all GPUs. This benchmark context is starkly different. The GT 545's nearest rivals are the NVIDIA RTX 5000 Mobile Ada Generation (average score 3596, just 0.1% higher), the NVIDIA GeForce GT 735M (average score 3616, 0.6% higher), and the NVIDIA GeForce GTX 1050 (average score 3629, 1% higher). The GT 545 is remarkably close to these competitors, sitting within a 1.5% delta of all three. This indicates that, within its own benchmark suite, the GT 545 is performing at a level consistent with mobile and entry-level desktop parts from much later generations.

The performance gulf between the two cards becomes apparent when examining their compute capabilities. The RTX 5080 SUPER delivers 56.28 TFLOPS of FP32 performance, while the GT 545 manages only 414.7 GFLOPS (0.4147 TFLOPS). This is a difference of over 135 times in raw floating-point throughput. The RTX 5080 SUPER also has a texture rate of 879.3 GTexel/s and a pixel rate of 293.1 GPixel/s, compared to the GT 545's 17.28 GTexel/s and 4.320 GPixel/s. In every measurable compute metric, the RTX 5080 SUPER is orders of magnitude ahead.

FAQ

Q: How does the RTX 5080 SUPER's benchmark score compare to its closest rivals?

A: The RTX 5080 SUPER scores 3075 in 3DMark Steel Nomad, which is 2.8% behind the NVIDIA Quadro P1000 (3163) and 3.4% behind the Intel Arc Pro B60 (3182). It is 3.1% ahead of the NVIDIA GeForce 820A (2983) and 3.6% ahead of the NVIDIA GeForce GTX 860M (2967).

Q: What is the GT 545's standing relative to its nearest competitors?

A: With a Geekbench OpenCL score of 3594, the GT 545 is nearly identical to the NVIDIA RTX 5000 Mobile Ada Generation (3596, 0.1% slower). It also trails the NVIDIA GeForce GT 735M (3616) by 0.6% and the NVIDIA GeForce GTX 1050 (3629) by 1%, while sitting 1.5% behind the AMD Radeon HD 6770 (3649).

Q: Which card has a higher percentile ranking among all GPUs?

A: The GT 545 holds a 21st percentile ranking, while the RTX 5080 SUPER holds a 19th percentile ranking. This suggests that, relative to their respective benchmark pools, the GT 545 scores slightly better than the RTX 5080 SUPER.

Q: Is there any benchmark where both cards were tested identically?

A: No. The FACT PACK lists a single benchmark for each card, but they are from different suites: the RTX 5080 SUPER uses 3dmark_3dmark_steel_nomad_dx12, and the GT 545 uses geekbench_opencl. The headToHeadBenchmarks field is empty, indicating no shared tests.

Q: What is the difference in FP32 compute performance between the two cards?

A: The RTX 5080 SUPER achieves 56.28 TFLOPS of FP32 compute, while the GT 545 achieves 414.7 GFLOPS. This means the RTX 5080 SUPER has roughly 135 times the raw FP32 throughput of the GT 545.

Q: How do the memory systems of the two cards differ?

A: The RTX 5080 SUPER features 24 GB of GDDR7 memory on a 256-bit bus, delivering 1.02 TB/s of bandwidth. The GT 545 features 1536 MB of DDR3 memory on a 192-bit bus, delivering 38.40 GB/s of bandwidth. The RTX 5080 SUPER has over 26 times the memory bandwidth.

Where Each One Wins

The RTX 5080 SUPER is the clear winner in every modern workload scenario. Its 24 GB VRAM capacity and 1.02 TB/s bandwidth are suited for high-resolution texture streaming and large dataset manipulation, whereas the GT 545's 1536 MB and 38.40 GB/s are a legacy limitation. In compute-heavy tasks, the RTX 5080 SUPER's 56.28 TFLOPS FP32 performance dwarfs the GT 545's 414.7 GFLOPS, making the newer card superior for any GPU-accelerated processing. The RTX 5080 SUPER also has dedicated RT cores (84) and tensor cores (336), which enable ray tracing and AI-accelerated features—capabilities the GT 545 lacks entirely. The RTX 5080 SUPER supports DirectX 12 Ultimate (12_2) and Vulkan 1.4, while the GT 545 only reaches DirectX 12 (11_0) and has no Vulkan support, meaning modern game features are out of reach for the older card.

The GT 545 does have one arena where it wins: energy efficiency relative to its age. Its TDP is 70 W, compared to the RTX 5080 SUPER's 415 W. It also draws power directly from the PCIe slot, requiring no external power connectors, and fits in a single-slot form factor. For legacy systems or tasks that require only basic 2D acceleration or very old DirectX 11 titles, the GT 545 is a functional, low-power option. However, in terms of absolute performance, the GT 545's only "win" is in its percentile score (21st vs 19th), which is an artifact of the different benchmark suites rather than a meaningful performance advantage.

Specification Differences

The two cards differ in nearly every specification category. The RTX 5080 SUPER has 10752 shading units, 336 TMUs, and 112 ROPs, while the GT 545 has 144 shading units, 24 TMUs, and 16 ROPs. The RTX 5080 SUPER's boost clock is 2617 MHz with a base clock of 2295 MHz, whereas the GT 545 has no listed base or boost clocks, only a memory clock of 800 MHz (1600 Mbps effective). The RTX 5080 SUPER's memory clock is 2000 MHz (32 Gbps effective). The memory configuration is also vastly different: 24 GB GDDR7 on a 256-bit bus versus 1536 MB DDR3 on a 192-bit bus. The RTX 5080 SUPER is a dual-slot card measuring 304 mm in length, while the GT 545 is a single-slot card at 145 mm. The RTX 5080 SUPER requires a 16-pin power connector, while the GT 545 has no power connectors and a suggested PSU of 250 W. The RTX 5080 SUPER uses a PCIe 5.0 x16 interface, compared to the GT 545's PCIe 2.0 x16. Display outputs also differ: the RTX 5080 SUPER offers 1x HDMI 2.1b and 3x DisplayPort 2.1b, while the GT 545 offers 1x DVI, 1x HDMI 1.3a, and 1x VGA.

Architecture Differences

The architectural divide is generational. The RTX 5080 SUPER is built on the GB203 chip using Blackwell 2.0 architecture, fabricated on a 5 nm process at TSMC. It contains 45,600 million transistors on a 378 mm² die, resulting in a transistor density of 120.6M per mm². The GT 545 uses the GF116 chip with Fermi 2.0 architecture, built on a 40 nm process, also at TSMC. It contains 1,170 million transistors on a 238 mm² die, yielding a transistor density of just 4.9M per mm². This means the RTX 5080 SUPER packs over 24 times more transistors per square millimeter. The RTX 5080 SUPER includes 84 RT cores and 336 tensor cores, while the GT 545 has neither. The RTX 5080 SUPER supports FP16 compute at a 1:1 ratio with FP32 (56.28 TFLOPS), whereas the GT 545 has no listed FP16 capability. The RTX 5080 SUPER is also a current "Active" production part from the GeForce 50-series, while the GT 545 is "End-of-life" from the GeForce 500-series, succeeding the GeForce 400 and preceding the GeForce 600.

The Verdict

The data is unambiguous: the NVIDIA GeForce RTX 5080 SUPER is a massively more powerful GPU than the GT 545. Its FP32 compute is over 135 times higher, its memory bandwidth is over 26 times higher, and its transistor count is nearly 39 times higher. The RTX 5080 SUPER is designed for modern gaming, ray tracing, and AI workloads, all of which are impossible on the GT 545. The GT 545, by contrast, is a relic of the Fermi era, with its nearest rivals being mobile and entry-level cards from much later generations—yet it still scores at a comparable level to them, indicating its performance was modest even for its time. The RTX 5080 SUPER's 19th percentile ranking in its own benchmark pool is curious, but the absolute performance figures dwarf the GT 545's output. For anyone building a modern system, the RTX 5080 SUPER is the only viable choice. The GT 545 should be considered solely for retro computing or as a display-output card for legacy systems, where its 70 W power draw and single-slot design are advantages. The verdict is not close: the RTX 5080 SUPER wins on every meaningful performance metric, while the GT 545's only claim is its lower power footprint and the historical context of its 2011 release date.

DETAILED SPECIFICATIONS

SPECIFICATION
GT 545
RTX 5080 SUPER
Core Specs
Shading Units
144
10,752 +7366.7%
Shaders
144
10,752 +7366.7%
TMUs
24
336 +1300.0%
ROPs
16
112 +600.0%
SM Count
3
—
Clocks
Base Clock
—
2295 MHz
Boost Clock
—
2617 MHz
GPU Clock
720 MHz
—
Shader Clock
1440 MHz
—
Memory Clock
800 MHz 1600 Mbps effective
2000 MHz 32 Gbps effective
Memory
Memory Size
1536 MB
24 GB
VRAM (MB)
1,536
24,576 +1500.0%
Memory Type
DDR3
GDDR7
Memory Bus
192 bit
256 bit
Bandwidth
38.40 GB/s
1.02 TB/s
Cache
L1 Cache
64 KB (per SM)
128 KB (per SM)
L2 Cache
384 KB
64 MB
Performance
Pixel Rate
4.320 GPixel/s
293.1 GPixel/s
Texture Rate
17.28 GTexel/s
879.3 GTexel/s
FP32 (TFLOPS)
414.7 GFLOPS
56.28 TFLOPS
FP64 (TFLOPS)
34.56 GFLOPS (1:12)
879.3 GFLOPS (1:64)
FP16 (TFLOPS)
—
56.28 TFLOPS (1:1)
AI/RT
RT Cores
—
84
Tensor Cores
—
336
Power
TDP
70 W
415 W
TDP (W)
70
415 +492.9%
Suggested PSU
250 W
—
Power Connectors
None
1x 16-pin
Architecture
Architecture
Fermi 2.0
Blackwell 2.0
GPU Name
GF116
GB203
Generation
GeForce 500
GeForce 50
Process Size
40 nm
5 nm
Transistors
1,170 million
45,600 million
Die Size
238 mm²
378 mm²
Foundry
TSMC
TSMC
Density
4.9M / mm²
120.6M / mm²
API Support
DirectX
12 (11_0)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
—
1.4
OpenCL
1.1
3.0
CUDA
2.1
—
Shader Model
5.1
6.8
Physical
Slot Width
Single-slot
Dual-slot
Length
145 mm 5.7 inches
304 mm 12 inches
Height
—
137 mm 5.4 inches
Outputs
1x DVI1x HDMI 1.3a1x VGA
1x HDMI 2.1b 3x DisplayPort 2.1b
Bus Interface
PCIe 2.0 x16
PCIe 5.0 x16
Other
Launch Price
149 USD
999 USD
Production
End-of-life
Active
Predecessor
GeForce 400
—
Successor
GeForce 600
—
View GeForce GT 545 Details View GeForce RTX 5080 SUPER Details