NVIDIA GeForce RTX 2080 vs NVIDIA GeForce RTX 3070 Ti Mobile Comparison

The NVIDIA GeForce RTX 3070 Ti Mobile and the NVIDIA GeForce RTX 2080 are close competitors in the benchmark database, with the desktop RTX 2080 winning 7 of 10 head-to-head tests, but the mobile 3070 Ti taking the decisive modern DirectX 12 workload by a wide margin. The RTX 3070 Ti Mobile posts an average benchmark score of 23518, slightly ahead of the RTX 2080’s 22895, while the RTX 2080 holds a marginal edge in overall percentile ranking at 68 vs 69 for the mobile part. The data reveals a generational split: the Ampere-based mobile chip dominates in newer APIs and compute tasks, while the older Turing desktop card retains advantages in legacy and 2D workloads.

Head-to-Head Benchmarks

The single largest performance gap appears in the 3DMark Steel Nomad DX12 test, where the RTX 3070 Ti Mobile scores 2572 against the RTX 2080’s 1752, a decisive 46.8% advantage. This is the clearest indicator of architectural superiority, as the mobile Ampere part leverages its higher FP32 throughput and newer feature set to crush the desktop Turing card in a modern, compute-heavy DirectX 12 scenario. No other test comes close to this margin, underscoring that the 3070 Ti Mobile is built for current-generation workloads.

The RTX 3070 Ti Mobile also wins in Geekbench OpenCL, scoring 106022 versus 91313, a 16.1% lead that reflects its stronger raw compute capability. The mobile part’s 16.60 TFLOPS FP32 performance versus the RTX 2080’s 10.07 TFLOPS explains this gap, as does the 3070 Ti Mobile’s 5888 shading units compared to 2944 on the desktop card. In Passmark DirectX 12, the mobile chip wins narrowly, 73 to 72 (1.4% delta), showing near-parity in that specific API path despite the larger differences elsewhere.

The RTX 2080 fights back across the majority of tests, though with much smaller margins. Its biggest win is in Passmark DirectX 9, scoring 223 against 196 (12.1% ahead), a legacy workload where the older architecture’s higher base clock of 1515 MHz and boost of 1710 MHz likely help. The desktop card also leads in Passmark G2D, 907 to 783 (13.7% ahead), indicating better 2D rasterization performance. In Geekbench Vulkan, the RTX 2080 wins 107797 to 100027, a 7.2% margin that suggests its 368 tensor cores and higher memory clock architecture still excel in certain compute paths.

The remaining wins for the RTX 2080 are modest: Passmark DirectX 10 (136 vs 124, 8.8% ahead), Passmark DirectX 11 (158 vs 153, 3.2% ahead), Passmark G3D (18720 vs 17727, 5.3% ahead), and Passmark GPU Compute (7872 vs 7504, 4.7% ahead). The G3D result is particularly notable because it is the most common overall gaming metric, and the RTX 2080’s lead there contradicts the average score advantage held by the mobile part. This suggests that while the 3070 Ti Mobile excels in specific modern benchmarks, the RTX 2080 delivers more consistent performance across a broader set of traditional workloads.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce RTX 3070 Ti Mobile has an average benchmark score of 23518, while the RTX 2080 scores 22895, giving the mobile part a lead of roughly 2.7%.

Q: How large is the performance gap in the 3DMark Steel Nomad DX12 test?

A: The RTX 3070 Ti Mobile scores 2572 versus the RTX 2080’s 1752, a 46.8% difference that represents the single largest head-to-head margin in the data.

Q: Does the RTX 2080 win any modern API benchmarks?

A: Yes, the RTX 2080 wins Geekbench Vulkan with a score of 107797 compared to the 3070 Ti Mobile’s 100027, a 7.2% advantage.

Q: What is the transistor density difference between the two GPUs?

A: The RTX 3070 Ti Mobile, built on an 8 nm process, has a transistor density of 44.4M per mm², while the 12 nm RTX 2080 achieves only 25.0M per mm².

Q: How do the two cards compare in Passmark G3D?

A: The RTX 2080 leads in Passmark G3D with a score of 18720 versus 17727 for the RTX 3070 Ti Mobile, a 5.3% margin in favor of the desktop card.

Q: Which GPU has more tensor cores?

A: The RTX 2080 has 368 tensor cores, while the RTX 3070 Ti Mobile has 184, giving the older desktop card a 2:1 advantage in that specific hardware count.

Where Each One Wins

The RTX 3070 Ti Mobile is the clear winner in modern DirectX 12 and compute-heavy scenarios. Its 46.8% lead in 3DMark Steel Nomad DX12 is the headline result, and its 16.1% advantage in Geekbench OpenCL reinforces its strength in parallel compute tasks. The mobile Ampere chip’s 16.60 TFLOPS FP32 and 16.60 TFLOPS FP16 (1:1) performance means it processes both data types at the same rate, a key advantage over the RTX 2080’s 2:1 FP16 ratio (20.14 TFLOPS FP16 vs 10.07 TFLOPS FP32). For users running the latest DirectX 12 titles or GPU-accelerated compute workloads, the 3070 Ti Mobile is the better choice.

The RTX 2080 dominates legacy and 2D workloads. It wins Passmark DirectX 9 by 12.1%, Passmark G2D by 13.7%, and holds smaller leads in DirectX 10 (8.8%), DirectX 11 (3.2%), and DirectX 12 (1.4% loss). Its Passmark G3D win of 5.3% is significant for gaming, as this test aggregates multiple DirectX versions and represents a more balanced view of overall 3D performance. The RTX 2080 also wins Geekbench Vulkan by 7.2%, suggesting its 368 tensor cores provide an advantage in Vulkan compute paths. For users prioritizing broad compatibility with older games and applications, the desktop RTX 2080 has the edge.

The split is largely generational: the mobile part wins where modern APIs and raw compute matter, while the desktop card wins where clock speed and legacy optimizations dominate. The RTX 2080’s higher boost clock of 1710 MHz versus 1410 MHz on the 3070 Ti Mobile likely explains its wins in older DirectX versions that are less parallel and more clock-sensitive.

Specification Differences

The two GPUs differ fundamentally in their core configurations. The RTX 3070 Ti Mobile has 5888 shading units, 184 TMUs, and 96 ROPs, while the RTX 2080 has 2944 shading units, 184 TMUs, and 64 ROPs. The mobile part doubles the shader count and adds 50% more ROPs, which explains its higher pixel rate of 135.4 GPixel/s versus 109.4 GPixel/s on the desktop card. However, the RTX 2080 has a higher texture rate at 314.6 GTexel/s compared to 259.4 GTexel/s, despite matching TMU count, due to its higher clock speeds.

Memory configurations are identical in capacity and bandwidth: both use 8 GB of GDDR6 on a 256-bit bus with 448.0 GB/s bandwidth and 14 Gbps effective memory speed. The RTX 3070 Ti Mobile has 46 ray tracing cores, matching the RTX 2080’s 46, but the desktop card has 368 tensor cores versus 184 on the mobile part. Power and physical specifications differ sharply: the 3070 Ti Mobile has a TDP of 115 W with no power connectors, while the RTX 2080 draws 215 W and requires a 1x 6-pin plus 1x 8-pin power setup with a suggested 550 W PSU. The RTX 2080 is a dual-slot card measuring 267 mm in length, 116 mm in height, and 35 mm in width, while the mobile part has no listed dimensions. The bus interface differs as well: PCIe 4.0 x16 for the 3070 Ti Mobile versus PCIe 3.0 x16 for the RTX 2080.

Architecture Differences

The architectural split is clear: the RTX 3070 Ti Mobile uses the GA104 chip on an 8 nm Samsung process with 17,400 million transistors on a 392 mm² die, while the RTX 2080 uses the TU104 chip on a 12 nm TSMC process with 13,600 million transistors on a much larger 545 mm² die. The transistor density difference is dramatic — 44.4M per mm² for the Ampere part versus 25.0M per mm² for Turing — reflecting the manufacturing process advantage. Despite having 3,800 million more transistors, the 3070 Ti Mobile’s die is 153 mm² smaller, proof of the 8 nm node’s efficiency.

The FP32 compute capacity tells the story of the generational leap: the 3070 Ti Mobile delivers 16.60 TFLOPS, while the RTX 2080 manages 10.07 TFLOPS — a 65% advantage for the mobile part. However, the RTX 2080’s FP16 performance of 20.14 TFLOPS (2:1 ratio) exceeds the 3070 Ti Mobile’s 16.60 TFLOPS (1:1 ratio), meaning the older card can process half-precision data faster when that path is utilized. The RTX 2080 also has double the tensor cores (368 vs 184), which may explain its Vulkan win. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, but the 3070 Ti Mobile is from the GeForce 30 Mobile generation with Ampere architecture, while the RTX 2080 is Turing from the GeForce 20 generation.

The RTX 2080’s predecessor is GeForce 10, and its successor is GeForce 30, placing it directly in line before the 3070 Ti Mobile’s generation. The 3070 Ti Mobile’s predecessor is GeForce 20 Mobile, confirming its position as a direct upgrade path. Both are end-of-life products, with the RTX 3070 Ti Mobile releasing on 2022-01-03 and the RTX 2080 releasing on 2018-09-19.

The Verdict

The data favors the RTX 3070 Ti Mobile for users focused on modern DirectX 12 gaming and compute workloads. Its 46.8% lead in 3DMark Steel Nomad DX12 and 16.1% advantage in Geekbench OpenCL are decisive, and its higher average benchmark score (23518 vs 22895) confirms overall superiority despite losing the majority of individual tests. The mobile part’s 8 nm process, higher shader count, and doubled FP32 throughput make it the more future-proof choice for current-generation software.

The RTX 2080 is the better pick for users whose workloads span legacy DirectX versions, 2D applications, or Vulkan compute. Its wins in DirectX 9 (12.1%), G2D (13.7%), and Vulkan (7.2%) show clear strengths, and its Passmark G3D lead of 5.3% indicates more consistent traditional gaming performance. The desktop card’s higher clocks (1515 MHz base, 1710 MHz boost) and double tensor core count (368 vs 184) provide advantages in clock-sensitive and AI-accelerated tasks. Its 215 W TDP and dual-slot design also indicate a higher power ceiling for sustained performance.

The choice comes down to workload focus. If the priority is playing the latest DirectX 12 titles or running GPU compute, the RTX 3070 Ti Mobile’s massive Steel Nomad lead and higher FP32 output make it the obvious winner. If the priority is a broad library of older games, 2D productivity, or Vulkan-based applications, the RTX 2080’s consistent wins across seven of ten tests and its 68th percentile ranking versus the mobile part’s 69th make it a compelling option. The RTX 2080’s launch MSRP was 699 USD, though its current end-of-life status means pricing dynamics have shifted.