NVIDIA GeForce RTX 2070 vs NVIDIA GeForce RTX 3060 Mobile Comparison

The NVIDIA GeForce RTX 2070 and NVIDIA GeForce RTX 3060 Mobile are two very different products that happen to share a similar performance tier. The RTX 2070 is a desktop card from the Turing generation, while the RTX 3060 Mobile is a laptop part from the Ampere generation. The benchmark data shows a clear split: the desktop RTX 2070 wins 9 out of 10 head-to-head tests, but the mobile RTX 3060 takes the most modern DirectX 12 test. This page breaks down exactly where each GPU excels, what architectural changes drove those results, and which type of user should prefer which card.

Head-to-Head Benchmarks

The most striking result is in the 3DMark Steel Nomad DX12 test, where the RTX 3060 Mobile wins with a score of 1821 against the RTX 2070's 1569. That is a 13.8% margin in favor of the laptop chip, and it is the only test the RTX 2070 loses. This suggests the newer Ampere architecture handles modern, heavily-threaded DX12 workloads more efficiently, even at lower clock speeds and with a smaller memory bus.

Everywhere else, the RTX 2070 dominates, often by substantial margins. The biggest victory is in Passmark DirectX 9, where the RTX 2070 scores 211 versus 146 for the RTX 3060 Mobile, a 44.5% lead. This is a massive gap and indicates that legacy DirectX 9 titles run far better on the older desktop card. Similarly, in Passmark G2D, the RTX 2070 posts 819 against 588, a 39.3% advantage, which points to a significant difference in 2D performance and memory bandwidth handling.

In the mainstream gaming metric of Passmark G3D, the RTX 2070 scores 16094 against 13230, giving it a 21.6% lead. The gap narrows in compute-oriented tests but remains in the RTX 2070's favor: Passmark GPU Compute shows 6411 versus 5718, a 12.1% difference. The DirectX 11 test shows a 17.3% lead (129 vs 110), and DirectX 10 shows a 23.3% lead (111 vs 90). Even the DirectX 12 test in Passmark goes to the RTX 2070, albeit narrowly at 60 versus 58 (3.4%). The compute API scores are closer: Geekbench OpenCL is 79966 for the RTX 2070 versus 79483 for the RTX 3060 Mobile (0.6% lead), and Geekbench Vulkan is 82521 versus 80344 (2.7% lead). Overall, the average benchmark score for the RTX 2070 is 18789, placing it at the 63rd percentile of all GPUs, while the RTX 3060 Mobile averages 18159, at the 62nd percentile. The RTX 2070's nearest rival is the NVIDIA RTX 2000 Ada Generation at 18954 (-0.9% delta), while the RTX 3060 Mobile sits closest to the AMD Radeon Pro 5700 at 18189 (-0.2% delta).

FAQ

Q: Which card is faster in modern DirectX 12 Ultimate workloads?

A: The RTX 3060 Mobile. In the 3DMark Steel Nomad DX12 test, it scores 1821 versus the RTX 2070's 1569, a 13.8% advantage. This is the only head-to-head test where the mobile card wins.

Q: Is the desktop RTX 2070 better for older games?

A: Yes, decisively. In Passmark DirectX 9, the RTX 2070 scores 211 versus 146, a 44.5% lead. It also wins DirectX 10 by 23.3% and DirectX 11 by 17.3%, showing a consistent advantage across legacy APIs.

Q: How do the two compare in raw compute performance?

A: The RTX 2070 leads in Passmark GPU Compute with 6411 versus 5718 (12.1%), but the gap is smaller in Geekbench OpenCL (79966 vs 79483, 0.6% lead) and Geekbench Vulkan (82521 vs 80344, 2.7% lead). The desktop card is generally ahead, but not by a huge margin in OpenCL.

Q: What are the overall performance percentiles?

A: The RTX 2070 sits at the 63rd percentile of all GPUs with an average score of 18789. The RTX 3060 Mobile is at the 62nd percentile with an average of 18159. They are statistically close, but the RTX 2070 edges ahead.

Q: Which card has higher memory bandwidth?

A: The RTX 2070 has a 256-bit bus providing 448.0 GB/s, while the RTX 3060 Mobile uses a 192-bit bus providing 336.0 GB/s. This 112 GB/s difference likely contributes to the RTX 2070's strong showing in bandwidth-sensitive 2D and legacy tests.

Q: Does the RTX 3060 Mobile have more shaders?

A: Yes, the RTX 3060 Mobile has 3840 shading units versus 2304 on the RTX 2070. Despite having 66% more shaders, the mobile card loses most tests, indicating that its lower clocks and memory bandwidth hold it back.

Architecture Differences

The two cards are built on entirely different architectures and processes. The RTX 2070 uses the TU106 chip on the Turing architecture, fabricated by TSMC on a 12 nm process. It packs 10,800 million transistors into a 445 mm² die, giving a transistor density of 24.3M per mm². In contrast, the RTX 3060 Mobile uses the GA106 chip on the Ampere architecture, built by Samsung on an 8 nm process. This smaller chip houses 12,000 million transistors on a 276 mm² die, achieving a much higher density of 43.5M per mm². The newer process allows the RTX 3060 Mobile to fit more transistors into a smaller space.

Core configuration differs significantly. The RTX 2070 has 2304 shading units, 144 TMUs, and 64 ROPs. It also features 36 RT cores and 288 tensor cores. The RTX 3060 Mobile has more shading units (3840), but fewer TMUs (120) and ROPs (48). It has 30 RT cores and 120 tensor cores. The RTX 3060 Mobile's FP32 throughput is 10.94 TFLOPS, which is higher than the RTX 2070's 7.465 TFLOPS, but its pixel rate is lower at 68.40 GPixel/s versus 103.7 GPixel/s, and its texture rate is lower at 171.0 GTexel/s versus 233.3 GTexel/s.

Memory architecture also diverges. Both use GDDR6, but the RTX 2070 has 8 GB on a 256-bit bus, while the RTX 3060 Mobile has 6 GB on a 192-bit bus. The memory clock is identical at 1750 MHz (14 Gbps effective), but the wider bus on the RTX 2070 yields 448.0 GB/s bandwidth versus 336.0 GB/s. The RTX 3060 Mobile supports PCIe 4.0 x16, while the RTX 2070 is limited to PCIe 3.0 x16. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Specification Differences

The most obvious difference is power. The RTX 2070 has a TDP of 175 W, requires a 1x 8-pin power connector, and needs a 450 W suggested PSU. The RTX 3060 Mobile has a TDP of just 80 W, uses no external power connectors (relying on the laptop's power delivery), and has no suggested PSU rating. This makes the RTX 3060 Mobile a far more power-efficient part.

Physical dimensions reflect their intended use cases. The RTX 2070 is a dual-slot desktop card measuring 229 mm in length, 113 mm in height, and 35 mm in width. The RTX 3060 Mobile has no listed dimensions, as it is a mobile BGA chip soldered to a laptop motherboard. Display outputs also differ: the RTX 2070 features 1x DVI, 1x HDMI 2.0, 2x DisplayPort 1.4a, and 1x USB Type-C, while the RTX 3060 Mobile's outputs are listed as "Portable Device Dependent," meaning they vary by laptop design.

Clock speeds are notably different. The RTX 2070 runs at a 1410 MHz base and 1620 MHz boost, while the RTX 3060 Mobile has a 900 MHz base and 1425 MHz boost. Despite the lower clocks, the RTX 3060 Mobile achieves higher FP32 throughput due to its larger shader count. The RTX 2070 was released on 2018-10-16 and is end-of-life, while the RTX 3060 Mobile launched on 2021-01-11 and is also end-of-life. The RTX 2070 had a launch MSRP of 499 USD; no MSRP is listed for the RTX 3060 Mobile.

The Verdict

The data points to a clear verdict for different use cases. If you are playing modern DX12 titles, the RTX 3060 Mobile is the better performer, as evidenced by its 13.8% win in 3DMark Steel Nomad. However, for virtually everything else, the RTX 2070 is faster. It wins 9 of 10 head-to-head tests, with particularly large margins in DirectX 9 (44.5%), G2D (39.3%), and G3D (21.6%). The RTX 2070 also has more memory (8 GB vs 6 GB) and higher bandwidth (448.0 GB/s vs 336.0 GB/s), which helps in texture-heavy and high-resolution scenarios.

The RTX 3060 Mobile compensates with dramatically lower power consumption (80 W vs 175 W), which makes it suitable for laptops where thermal and power budgets are tight. The RTX 2070 is a desktop card that requires a dedicated PSU and cooling solution. For a desktop builder prioritizing legacy game compatibility and overall rasterization performance, the RTX 2070 is the stronger choice. For a laptop buyer who needs a modern, efficient GPU that handles DX12 well, the RTX 3060 Mobile is the practical option.

Where Each One Wins

NVIDIA GeForce RTX 2070 wins in: Legacy API performance (DirectX 9, 10, 11), 2D performance, overall 3D performance, compute workloads (Passmark GPU Compute), and OpenCL/Vulkan compute. It also wins on memory capacity (8 GB) and bandwidth (448.0 GB/s). Its higher base and boost clocks (1410/1620 MHz) contribute to its dominance in these tests. It is the better card for gamers with older titles or those who want maximum desktop rasterization performance.

NVIDIA GeForce RTX 3060 Mobile wins in: Modern DX12 Ultimate workloads (3DMark Steel Nomad), with a 13.8% lead. It also wins on efficiency, with an 80 W TDP versus 175 W, making it the only viable option for thin-and-light laptops. Its higher shader count (3840) and FP32 throughput (10.94 TFLOPS) give it an edge in compute-heavy DX12 titles that leverage the new architecture. It supports PCIe 4.0, which can be beneficial in systems with fast NVMe storage or future expansion. For laptop users prioritizing battery life and modern game compatibility, this is the clear winner.