NVIDIA GeForce GTX 980 Ti vs NVIDIA GeForce RTX 4070 Mobile Comparison

The NVIDIA GeForce GTX 980 Ti and the NVIDIA GeForce RTX 4070 Mobile represent two distinct eras of GPU design, separated by nearly eight years of architectural evolution. The data shows a clear generational leap in raw compute capability, but the comparison is nuanced by differences in form factor, feature set, and target use case. This analysis examines the benchmark scores, architectural differences, and specification changes to determine where each card excels.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce GTX 980 Ti has a higher average benchmark score of 28,020, compared to the NVIDIA GeForce RTX 4070 Mobile's 27,435. This places both cards at the 73rd percentile among all GPUs, indicating they perform in a similar overall tier despite their generational gap.

Q: How large is the performance gap in the head-to-head tests?

A: The RTX 4070 Mobile wins both head-to-head tests decisively. In Geekbench OpenCL, it scores 109,197 versus 43,513 for the GTX 980 Ti, a delta of -60.2% (meaning the 980 Ti trails by that margin). In Geekbench Vulkan, the RTX 4070 Mobile scores 108,367 versus 47,724, a delta of -56%.

Q: Which card has more shading units?

A: The RTX 4070 Mobile has 4,608 shading units, significantly more than the GTX 980 Ti's 2,816. However, the GTX 980 Ti has more texture mapping units (176 vs. 144) and more render output units (96 vs. 48).

Q: Do both cards support the same graphics APIs?

A: No. The GTX 980 Ti supports DirectX 12 (12_1), while the RTX 4070 Mobile supports DirectX 12 Ultimate (12_2). Both support OpenGL 4.6 and Vulkan 1.4, but the DirectX feature level differs, with the RTX 4070 Mobile being more modern.

Q: What is the difference in process node technology?

A: The GTX 980 Ti uses a 28 nm process from TSMC, while the RTX 4070 Mobile uses a 5 nm process, also from TSMC. This is a major factor in the RTX 4070 Mobile's higher transistor density of 121.8M / mm² versus 13.3M / mm² for the GTX 980 Ti.

Q: Which card has higher memory bandwidth?

A: The GTX 980 Ti has higher memory bandwidth at 336.6 GB/s, thanks to a 384-bit bus, compared to the RTX 4070 Mobile's 256.0 GB/s on a 128-bit bus. The RTX 4070 Mobile compensates with faster GDDR6 memory at 16 Gbps effective versus 7 Gbps on the GTX 980 Ti.

Architecture Differences

The architectural divide between the GTX 980 Ti and RTX 4070 Mobile is substantial. The GTX 980 Ti is built on the Maxwell 2.0 architecture using the GM200 chip, fabricated on a 28 nm process at TSMC. This process yields a large die of 601 mm² housing 8,000 million transistors, resulting in a modest transistor density of 13.3M / mm². In contrast, the RTX 4070 Mobile uses the Ada Lovelace architecture with the AD106 chip, built on a 5 nm process. This allows for a much smaller die of 188 mm² while packing 22,900 million transistors, achieving a density of 121.8M / mm² — a massive improvement in efficiency.

The feature sets diverge sharply. The RTX 4070 Mobile includes 36 ray tracing cores and 144 tensor cores, which are entirely absent from the GTX 980 Ti. This enables hardware-accelerated ray tracing and AI-driven features like DLSS on the newer card. The GTX 980 Ti predates these technologies, relying purely on traditional rasterization. Additionally, the RTX 4070 Mobile supports DirectX 12 Ultimate (12_2), which includes features like mesh shaders and variable rate shading, while the GTX 980 Ti is limited to DirectX 12 (12_1).

Clock speeds and compute rates also show the generational leap. The GTX 980 Ti has a base clock of 1000 MHz and boost of 1076 MHz, while the RTX 4070 Mobile runs at 1395 MHz base and 1695 MHz boost. This translates to FP32 compute of 6.060 TFLOPS for the GTX 980 Ti versus 15.62 TFLOPS for the RTX 4070 Mobile. The RTX 4070 Mobile also offers FP16 at 15.62 TFLOPS (1:1), a capability the GTX 980 Ti lacks entirely.

Head-to-Head Benchmarks

The data provides two direct comparisons, and the RTX 4070 Mobile dominates both. In Geekbench OpenCL, the RTX 4070 Mobile scores 109,197 versus the GTX 980 Ti's 43,513. This represents a delta of -60.2%, meaning the GTX 980 Ti's score is roughly 60% lower. In raw terms, the RTX 4070 Mobile is 2.5 times faster in this compute-heavy test. The result aligns with the FP32 throughput figures, where the RTX 4070 Mobile's 15.62 TFLOPS is more than double the GTX 980 Ti's 6.060 TFLOPS.

The Geekbench Vulkan test tells a similar story. The RTX 4070 Mobile scores 108,367, while the GTX 980 Ti manages 47,724 — a delta of -56%. While the gap is slightly narrower than in OpenCL, it remains a decisive victory for the newer card. This suggests the RTX 4070 Mobile's architecture handles modern API workloads more efficiently, likely benefiting from the newer process node and higher clock speeds.

Notably, the GTX 980 Ti has no wins in the head-to-head benchmarks. Its higher pixel rate (103.3 GPixel/s vs. 81.36 GPixel/s) and higher memory bandwidth (336.6 GB/s vs. 256.0 GB/s) do not translate into benchmark victories in these tests. The RTX 4070 Mobile's superior texture rate (244.1 GTexel/s vs. 189.4 GTexel/s) and compute throughput prove more decisive in the measured workloads.

Specification Differences

The two GPUs differ across nearly every specification category. The process node sees the GTX 980 Ti at 28 nm versus the RTX 4070 Mobile at 5 nm. Transistor count jumps from 8,000 million to 22,900 million, while die size shrinks from 601 mm² to 188 mm². Transistor density increases from 13.3M / mm² to 121.8M / mm².

Clock speeds favor the RTX 4070 Mobile: base clock of 1395 MHz versus 1000 MHz, and boost clock of 1695 MHz versus 1076 MHz. Memory configuration also differs substantially. The GTX 980 Ti has 6 GB of GDDR5 on a 384-bit bus with 336.6 GB/s bandwidth, while the RTX 4070 Mobile has 8 GB of GDDR6 on a 128-bit bus with 256.0 GB/s bandwidth. The effective memory speed is 7 Gbps for the GTX 980 Ti and 16 Gbps for the RTX 4070 Mobile.

Core counts vary by type. The GTX 980 Ti has 2,816 shading units, 176 TMUs, and 96 ROPs. The RTX 4070 Mobile has 4,608 shading units, 144 TMUs, and 48 ROPs. The RTX 4070 Mobile also has 36 RT cores and 144 tensor cores. Fill rates reflect these differences: pixel rate is 103.3 GPixel/s for the GTX 980 Ti versus 81.36 GPixel/s for the RTX 4070 Mobile; texture rate is 189.4 GTexel/s versus 244.1 GTexel/s.

Power and physical specifications are starkly different. The GTX 980 Ti has a 250 W TDP with dual-slot cooling and 1x 6-pin + 1x 8-pin power connectors, plus a suggested 600 W PSU. The RTX 4070 Mobile has a 115 W TDP, uses IGP slot width, has no power connectors, and lists no suggested PSU. The GTX 980 Ti has specific dimensions (267 mm length, 111 mm height, 40 mm width) and display outputs (1x DVI, 1x HDMI 2.0, 3x DisplayPort 1.2), while the RTX 4070 Mobile's outputs are described as "Portable Device Dependent" with no dimensions listed.

Where Each One Wins

The RTX 4070 Mobile wins decisively in compute-heavy benchmarks. Its Geekbench OpenCL and Vulkan scores are roughly 2.5x and 2.3x higher, respectively, than the GTX 980 Ti's. This makes it the clear choice for workloads that leverage raw shader throughput, such as modern game rendering, GPU-accelerated compute tasks, and applications that can utilize its FP16 capabilities. The presence of ray tracing cores and tensor cores also gives it a feature advantage for games and applications that support those technologies.

The GTX 980 Ti, despite losing the head-to-head benchmarks, holds advantages in specific areas. Its higher pixel rate (103.3 GPixel/s vs. 81.36 GPixel/s) and greater memory bandwidth (336.6 GB/s vs. 256.0 GB/s) suggest it may perform relatively better in bandwidth-sensitive scenarios or at high resolutions where pixel throughput matters. Its 96 ROPs versus 48 ROPs also favor it in traditional rasterization workloads that are fill-rate bound. The GTX 980 Ti's higher average benchmark score (28,020 vs. 27,435) indicates that in the broader benchmark suite, it edges out the RTX 4070 Mobile slightly, likely due to the GTX 980 Ti's strengths in legacy or fill-rate-oriented tests.

The Verdict

The data paints a clear picture: the RTX 4070 Mobile is the superior performer in modern compute workloads, with more than double the FP32 throughput and decisive wins in both head-to-head benchmark tests. Its 5 nm process, higher clock speeds, and dedicated ray tracing and tensor cores make it the more future-proof choice for gaming and GPU-accelerated applications. The RTX 4070 Mobile's lower TDP of 115 W versus 250 W also makes it significantly more power-efficient, though it is limited to a mobile form factor.

The GTX 980 Ti, however, is not without merit. Its higher pixel rate, memory bandwidth, and ROP count suggest it can hold its own in specific legacy or bandwidth-bound scenarios. Its higher average benchmark score indicates that, across a broader range of tests, it remains competitive despite its age. For users with older software that relies on fill-rate performance or those who require a desktop card with specific display outputs, the GTX 980 Ti may still be relevant. However, for anyone prioritizing raw compute performance, modern API support, or power efficiency, the data unambiguously favors the RTX 4070 Mobile.