NVIDIA GeForce GTX 980 Ti vs NVIDIA GeForce RTX 3080 Ti Mobile Comparison

Where Each One Wins

The benchmark data draws a stark, one-sided picture. The NVIDIA GeForce RTX 3080 Ti Mobile wins every single head-to-head test, leaving the GTX 980 Ti with zero victories across the three shared benchmarks. This is not a close contest; it is a generational sweep. The 3080 Ti Mobile’s dominance is most pronounced in compute-heavy workloads, where its Ampere architecture and much larger shader count translate into enormous leads.

In the 3DMark Steel Nomad DX12 test, the RTX 3080 Ti Mobile scores 2869 against the GTX 980 Ti’s 1321. That is a delta of -54% from the perspective of the older card, meaning the mobile part is more than twice as fast in this modern DirectX 12 rasterization workload. The GTX 980 Ti, despite being a desktop flagship with a 250 W TDP, cannot keep pace with a laptop GPU that draws less than half the power. This suggests that raw power draw is not the sole determinant of performance; architectural efficiency and feature support matter immensely.

The Geekbench OpenCL test reinforces this narrative. The RTX 3080 Ti Mobile posts 117866, while the GTX 980 Ti manages 43513. The delta here is -63.1%, the largest margin of any test. OpenCL is a general-purpose compute API, and the 3080 Ti Mobile’s 7424 shading units (versus 2816 on the 980 Ti) provide a massive parallelism advantage. The mobile GPU also benefits from 232 tensor cores and 58 RT cores, which, while not directly used in OpenCL, indicate a fundamentally more modern and flexible compute engine.

The Vulkan result is similarly lopsided. The RTX 3080 Ti Mobile scores 107502, and the GTX 980 Ti scores 47724, a delta of -55.6%. Vulkan is a low-overhead API that scales well with core counts, so the 3080 Ti Mobile’s superior shader and texture unit counts shine here. Notably, the GTX 980 Ti’s best showing is in Vulkan relative to its other scores—it achieves 47.7% of the mobile card’s performance in this test, versus 36.9% in OpenCL and 46.0% in Steel Nomad. This indicates the older Maxwell architecture is not entirely obsolete in modern APIs, but it is clearly outclassed.

The wins are not just about peak performance; they are about consistency. The RTX 3080 Ti Mobile wins by a wide margin in every category, from synthetic rasterization to compute. The GTX 980 Ti has no niche where it pulls ahead. Even in the PassMark tests that only the 3080 Ti Mobile has scores for (DirectX 9, 10, 11, 12, G2D, G3D, and GPU Compute), the numbers are respectable but not stellar, suggesting the mobile part is a well-rounded performer across legacy and modern workloads.

The Verdict

Who should pick which? The data is unambiguous. The RTX 3080 Ti Mobile is the superior card for virtually every use case. Its average benchmark score of 25740 is lower than the GTX 980 Ti’s 28020, but this is misleading because the mobile card’s average includes several low-scoring PassMark DirectX legacy tests (e.g., DirectX 9 at 201, DirectX 10 at 131) that drag its mean down. In the three tests where both cards are measured head-to-head, the mobile GPU wins by 54-63%. The GTX 980 Ti’s higher average is a statistical artifact of having a smaller, more favorable benchmark suite, not a sign of real-world superiority.

For gamers and professionals using modern APIs (DirectX 12, Vulkan), the RTX 3080 Ti Mobile is the clear choice. It delivers over twice the performance in Steel Nomad and 1.8x the performance in Vulkan. The mobile card also supports DirectX 12 Ultimate (12_2) with hardware ray tracing and variable rate shading, whereas the GTX 980 Ti is limited to DirectX 12 (12_1) without RT or tensor cores. If you need ray tracing, DLSS, or any AI-accelerated workload, the 3080 Ti Mobile is the only option.

For legacy software or pure OpenCL compute, the GTX 980 Ti’s higher average score might tempt some, but the head-to-head OpenCL result (43513 vs 117866) shows the mobile part is 2.7x faster in that API as well. There is no workload in the data where the GTX 980 Ti wins. The only reason to choose the desktop card is if you require its specific display outputs (1x DVI, 1x HDMI 2.0, 3x DisplayPort 1.2) or its dual-slot, desktop form factor—but those are physical constraints, not performance advantages.

The percentile ranks are close (73rd for the 980 Ti, 71st for the 3080 Ti Mobile), but this is because the mobile card is compared against all GPUs including much faster desktop parts. Within this direct comparison, the RTX 3080 Ti Mobile is the definitive winner. Its 16 GB of GDDR6 memory versus 6 GB of GDDR5 also means it can handle larger textures and datasets, a critical advantage in modern games and AI inference. The verdict is simple: the RTX 3080 Ti Mobile is the card to pick for any performance-sensitive task.

Head-to-Head Benchmarks

The largest victory for the RTX 3080 Ti Mobile comes in Geekbench OpenCL, where it scores 117866 against the GTX 980 Ti’s 43513. That is a 174% improvement for the mobile part (or a -63.1% delta for the desktop card). This massive gap is explained by the mobile GPU’s 7424 shading units, 232 TMUs, and 232 tensor cores, compared to 2816 shading units and 176 TMUs on the 980 Ti. The compute throughput is also stark: 18.71 TFLOPS FP32 on the mobile card versus 6.060 TFLOPS on the desktop card. That is over three times the raw compute, and OpenCL is a workload that scales almost linearly with shader count.

The second-largest win is in Geekbench Vulkan, where the RTX 3080 Ti Mobile scores 107502 versus 47724 for the GTX 980 Ti, a delta of -55.6%. Vulkan’s low overhead benefits the mobile card’s higher core count and newer architecture. The mobile GPU’s texture rate of 292.3 GTexel/s versus 189.4 GTexel/s on the 980 Ti means it can feed its shaders much faster in draw-call-heavy scenes. The pixel rate is closer (121.0 GPixel/s vs 103.3 GPixel/s), but the shader and texture advantages dominate.

The 3DMark Steel Nomad DX12 test shows the smallest margin of the three, but it is still a decisive win for the RTX 3080 Ti Mobile: 2869 versus 1321, a delta of -54%. This test is more rasterization-focused, and the mobile card’s 96 ROPs match the desktop card’s 96 ROPs exactly. However, the mobile GPU’s higher clock boost (1260 MHz vs 1076 MHz) and much higher FP32 throughput allow it to pull ahead. The memory bandwidth is also critical here: 512.0 GB/s on the mobile card versus 336.6 GB/s on the desktop card. In a bandwidth-sensitive test like Steel Nomad, that 52% bandwidth advantage helps explain the 117% performance lead.

It is notably the GTX 980 Ti has a higher base clock (1000 MHz vs 810 MHz) and a higher boost clock (1076 MHz vs 1260 MHz is actually lower for the mobile card’s base, but its boost is higher). Wait—the data shows the mobile card’s base clock is 810 MHz and boost is 1260 MHz, while the desktop card’s base is 1000 MHz and boost is 1076 MHz. So the mobile GPU has a 17% higher boost clock, which partially compensates for its lower base clock. But the real story is the shader count: 7424 versus 2816 is a 2.6x difference, and that dwarfs any clock speed considerations.

FAQ

Q: Which card has a higher average benchmark score?

A: The GTX 980 Ti has a higher average benchmark score of 28020, compared to the RTX 3080 Ti Mobile’s 25740. However, this is because the mobile card’s average includes several low-scoring legacy PassMark tests (DirectX 9: 201, DirectX 10: 131, DirectX 11: 164) that are not present in the desktop card’s benchmark suite.

Q: Does the RTX 3080 Ti Mobile support ray tracing?

A: Yes. The RTX 3080 Ti Mobile has 58 RT cores and 232 tensor cores, and supports DirectX 12 Ultimate (12_2). The GTX 980 Ti has no RT cores or tensor cores and is limited to DirectX 12 (12_1).

Q: How much faster is the RTX 3080 Ti Mobile in 3DMark Steel Nomad?

A: The RTX 3080 Ti Mobile scores 2869 versus 1321 for the GTX 980 Ti, a delta of -54% from the desktop card’s perspective. This means the mobile card is approximately 117% faster in this DirectX 12 test.

Q: What are the memory specifications of each card?

A: The GTX 980 Ti has 6 GB of GDDR5 memory on a 384-bit bus with 336.6 GB/s bandwidth. The RTX 3080 Ti Mobile has 16 GB of GDDR6 memory on a 256-bit bus with 512.0 GB/s bandwidth.

Q: Which card has a higher transistor density?

A: The RTX 3080 Ti Mobile has a transistor density of 44.4M per mm² (22,000 million transistors on a 496 mm² die, using Samsung’s 8 nm process). The GTX 980 Ti has 13.3M per mm² (8,000 million transistors on a 601 mm² die, using TSMC’s 28 nm process).

Q: What is the TDP difference between the two cards?

A: The GTX 980 Ti has a TDP of 250 W, while the RTX 3080 Ti Mobile has a TDP of 115 W. Despite drawing less than half the power, the mobile card outperforms the desktop card in every shared benchmark.

Architecture Differences

The two GPUs represent radically different eras of NVIDIA design. The GTX 980 Ti uses the GM200 chip on the Maxwell 2.0 architecture, built on TSMC’s 28 nm process. It packs 8,000 million transistors into a 601 mm² die, yielding a transistor density of 13.3 million per mm². The RTX 3080 Ti Mobile uses the GA103 chip on the Ampere architecture, built on Samsung’s 8 nm process. It contains 22,000 million transistors in a 496 mm² die, achieving a density of 44.4 million per mm²—over three times the density of the older chip.

The Maxwell architecture has no dedicated ray tracing or tensor cores. It relies on 2816 shading units, 176 TMUs, and 96 ROPs. The Ampere architecture in the 3080 Ti Mobile is fundamentally different: it includes 7424 shading units, 232 TMUs, 96 ROPs, plus 58 RT cores and 232 tensor cores. This means the mobile GPU can accelerate ray-traced workloads and AI-based features like DLSS, which the Maxwell card cannot do at all. The FP32 compute is also dramatically different: 6.060 TFLOPS for the 980 Ti versus 18.71 TFLOPS for the 3080 Ti Mobile, with the latter also supporting FP16 at a 1:1 ratio (18.71 TFLOPS), which the former does not list.

The process node difference is significant. The 28 nm TSMC process used for Maxwell is a decade-old technology, while the 8 nm Samsung process for Ampere allows for much higher transistor density and efficiency. This explains how the mobile card can have nearly three times the shading units and still draw only 115 W versus 250 W. The memory architecture also differs: the 980 Ti uses a 384-bit bus with GDDR5, while the 3080 Ti Mobile uses a narrower 256-bit bus but with faster GDDR6, resulting in higher bandwidth (512.0 GB/s vs 336.6 GB/s).

The API support reflects the generational gap. The GTX 980 Ti supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The RTX 3080 Ti Mobile supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The 12_2 feature level enables hardware ray tracing, mesh shaders, and variable rate shading—features that are completely absent on the Maxwell card. Additionally, the mobile GPU uses PCIe 4.0 x16, while the desktop card uses PCIe 3.0 x16, doubling the bus bandwidth for data transfers.

Specification Differences

The most obvious difference is the memory configuration. The GTX 980 Ti offers 6 GB of GDDR5 on a 384-bit bus, while the RTX 3080 Ti Mobile offers 16 GB of GDDR6 on a 256-bit bus. Despite the narrower bus, the mobile card’s memory bandwidth is 512.0 GB/s versus 336.6 GB/s, a 52% advantage. The memory clock also differs: the 980 Ti runs at 1753 MHz (7 Gbps effective), while the 3080 Ti Mobile runs at 2000 MHz (16 Gbps effective).

The compute resources are massively different. The GTX 980 Ti has 2816 shading units, 176 TMUs, and 96 ROPs. The RTX 3080 Ti Mobile has 7424 shading units, 232 TMUs, and 96 ROPs. The mobile card also has 58 RT cores and 232 tensor cores, which the desktop card lacks entirely. The pixel rate is close (103.3 GPixel/s vs 121.0 GPixel/s), but the texture rate is not (189.4 GTexel/s vs 292.3 GTexel/s). FP32 performance is 6.060 TFLOPS versus 18.71 TFLOPS, and the mobile card supports FP16 at 18.71 TFLOPS while the desktop card has no listed FP16.

Power and physical specifications differ starkly. The GTX 980 Ti has a 250 W TDP, requires a 600 W power supply, uses 1x 6-pin + 1x 8-pin power connectors, and is a dual-slot card measuring 267 mm in length. The RTX 3080 Ti Mobile has a 115 W TDP, uses no external power connectors, and has no listed dimensions or slot width—it is a portable device dependent component. The desktop card offers 1x DVI, 1x HDMI 2.0, and 3x DisplayPort 1.2 outputs, while the mobile card’s outputs are portable device dependent.

The process and die specifications are also different. The GTX 980 Ti uses TSMC’s 28 nm process, has a die size of 601 mm², and 8,000 million transistors. The RTX 3080 Ti Mobile uses Samsung’s 8 nm process, has a die size of 496 mm², and 22,000 million transistors. The bus interface differs too: PCIe 3.0 x16 for the desktop card versus PCIe 4.0 x16 for the mobile card. The release dates are also far apart: June 2015 for the 980 Ti versus January 2022 for the 3080 Ti Mobile. The GTX 980 Ti had a launch MSRP of 649 USD, while the mobile card has no listed launch MSRP.