NVIDIA GeForce RTX 2070 SUPER vs NVIDIA GeForce RTX 3060 Mobile Comparison

The NVIDIA GeForce RTX 2070 SUPER and NVIDIA GeForce RTX 3060 Mobile occupy different ends of the performance spectrum, despite their similar naming. The desktop RTX 2070 SUPER, a Turing-based card from 2019, wins 9 out of 10 head-to-head benchmark comparisons. The mobile RTX 3060, an Ampere part from 2021, takes a single victory in a modern DirectX 12 test. The data is clear: the 2070 SUPER is the faster card overall, but the 3060 Mobile shows where newer architecture can still pull ahead.

Where Each One Wins

The RTX 2070 SUPER dominates across nearly every workload category in the recorded benchmarks. Its wins are broad and decisive, covering legacy DirectX APIs, compute tasks, and general 2D performance. For users running older games or applications that rely on DirectX 9, 10, or 11, the 2070 SUPER is the clear choice. Its PassMark DirectX 9 score of 223 versus 146 for the 3060 Mobile represents a massive gap, and similar advantages appear in DirectX 10 (132 vs 90) and DirectX 11 (151 vs 110).

The 3060 Mobile's only win comes in the 3DMark Steel Nomad DX12 test, scoring 1821 against the 2070 SUPER's 1651. This is a 9.3% advantage for the mobile card. This suggests that in very specific, modern DirectX 12 workloads, the newer Ampere architecture can leverage its higher shader count and newer feature set to overcome the desktop card's raw power advantage. However, this is an isolated result; in the other DirectX 12 test (PassMark DirectX 12), the 2070 SUPER wins with a 15.5% margin.

The 2070 SUPER also wins in compute-heavy scenarios. Its PassMark GPU Compute score of 7557 beats the 3060 Mobile's 5718 by 32.2%. It also leads in Geekbench OpenCL (83358 vs 79483) and Geekbench Vulkan (90637 vs 80344). The overall average benchmark score tells the same story: the 2070 SUPER averages 20282, while the 3060 Mobile averages 18159, a difference of about 11.7% in favor of the desktop card.

Architecture Differences

The two cards are built on fundamentally different architectures and manufacturing processes. The RTX 2070 SUPER uses the TU104 chip on TSMC's 12 nm node, while the RTX 3060 Mobile uses the GA106 chip on Samsung's 8 nm node. This process difference is significant: the 3060 Mobile packs 12,000 million transistors into a 276 mm² die, giving it a transistor density of 43.5M per mm². The 2070 SUPER uses 13,600 million transistors across a much larger 545 mm² die, resulting in a lower density of 25.0M per mm². The newer node allows the mobile chip to be far more compact despite having nearly as many transistors.

The 3060 Mobile has more shading units (3840 versus 2560) and more tensor cores (120 versus 320? No, the 2070 SUPER has 320 tensor cores, the 3060 Mobile has 120). However, the 2070 SUPER has more RT cores (40 versus 30) and more texture mapping units (160 versus 120). The 2070 SUPER also has a higher number of ROPs (64 versus 48). The clock speeds differ dramatically: the 2070 SUPER runs at 1605 MHz base and 1770 MHz boost, while the 3060 Mobile runs at a much lower 900 MHz base and 1425 MHz boost. This clock advantage is a key reason the desktop card wins most benchmarks.

Memory configurations also differ. The 2070 SUPER has 8 GB of GDDR6 on a 256-bit bus, providing 448.0 GB/s of bandwidth. The 3060 Mobile has 6 GB of GDDR6 on a 192-bit bus, yielding 336.0 GB/s. Both use 14 Gbps effective memory speed, but the wider bus gives the 2070 SUPER a 33% bandwidth advantage. The 2070 SUPER also has a much higher TDP at 215 W, versus just 80 W for the 3060 Mobile, reflecting the power constraints of mobile designs.

Head-to-Head Benchmarks

The largest win for the RTX 2070 SUPER comes in PassMark DirectX 9, where it scores 223 against the 3060 Mobile's 146, a 52.7% advantage. This is followed closely by the PassMark G2D test, where the 2070 SUPER scores 878 versus 588, a 49.3% lead. The G2D test measures 2D performance, which is not typically the focus for gamers but matters for desktop productivity and certain applications.

In the more relevant 3D tests, the 2070 SUPER leads PassMark G3D with 18169 against 13230, a 37.3% margin. The same percentage appears in PassMark DirectX 11 (151 vs 110). PassMark DirectX 10 shows a 46.7% lead (132 vs 90). Compute performance favors the 2070 SUPER by 32.2% (7557 vs 5718). Vulkan performance shows a 12.8% advantage for the 2070 SUPER (90637 vs 80344), and OpenCL shows a smaller 4.9% lead (83358 vs 79483).

The 3060 Mobile's only win is in 3DMark Steel Nomad DX12, where it scores 1821 against 1651. This 9.3% margin is notable because it is the most modern test in the suite. It suggests that in newer DirectX 12 Ultimate workloads, the 3060 Mobile's Ampere architecture, with its 3840 shading units and higher FP32 throughput (10.94 TFLOPS versus 9.062 TFLOPS for the 2070 SUPER), can overcome the desktop card's clock speed and bandwidth advantages. The 3060 Mobile also has a higher FP16 rating at 10.94 TFLOPS (1:1), while the 2070 SUPER's FP16 is 18.12 TFLOPS (2:1), though this does not translate into benchmark wins.

The Verdict

The RTX 2070 SUPER is the stronger GPU for almost all purposes. Its wins in DirectX 9, 10, 11, and 12, plus compute and 2D tests, make it the more versatile card. Anyone building a desktop system and comparing these two should choose the 2070 SUPER without hesitation. The data shows it is faster in legacy titles, faster in current DirectX 11 games, and faster in compute workloads. Its 8 GB memory buffer and 448.0 GB/s bandwidth also provide more headroom for high-resolution textures and demanding settings.

The RTX 3060 Mobile is a different product for a different use case. Its single win in 3DMark Steel Nomad DX12 is a sign that it handles the newest DirectX 12 Ultimate features well. For a laptop, the 80 W TDP is a critical advantage, as it allows for thinner, cooler, and longer-lasting machines. The 3060 Mobile also supports PCIe 4.0 x16, while the 2070 SUPER is limited to PCIe 3.0 x16, which may matter for future expansion. But in pure performance terms, it trails the 2070 SUPER by roughly 11% on average.

Pick the RTX 2070 SUPER for maximum desktop performance. Pick the RTX 3060 Mobile if you need a laptop GPU with modern features and much lower power draw. The 2070 SUPER is end-of-life, as is the 3060 Mobile, so neither is a future-proof purchase. But if the choice is between these two, the data overwhelmingly favors the desktop card.

FAQ

Q: Which GPU is faster in DirectX 11 games?

A: The RTX 2070 SUPER is significantly faster. In PassMark DirectX 11, it scores 151 versus 110 for the RTX 3060 Mobile, a 37.3% advantage.

Q: Does the RTX 3060 Mobile ever beat the RTX 2070 SUPER?

A: Yes, in one test. The 3060 Mobile wins in 3DMark Steel Nomad DX12 with a score of 1821 against the 2070 SUPER's 1651, a 9.3% margin.

Q: How do the memory bandwidths compare?

A: The RTX 2070 SUPER has 448.0 GB/s of bandwidth with 8 GB of GDDR6 on a 256-bit bus. The RTX 3060 Mobile has 336.0 GB/s with 6 GB on a 192-bit bus.

Q: Which card has more shading units?

A: The RTX 3060 Mobile has 3840 shading units, while the RTX 2070 SUPER has 2560. Despite fewer units, the 2070 SUPER wins most benchmarks due to higher clock speeds.

Q: What is the TDP difference?

A: The RTX 2070 SUPER has a 215 W TDP, while the RTX 3060 Mobile has an 80 W TDP. This makes the mobile card far more power-efficient, though slower overall.

Q: Are these cards still in production?

A: No. Both are marked as end-of-life in the database. The RTX 2070 SUPER was released in July 2019, and the RTX 3060 Mobile was released in January 2021.

Specification Differences

• Chip: TU104 (2070 SUPER) vs GA106 (3060 Mobile)
• Architecture: Turing (2070 SUPER) vs Ampere (3060 Mobile)
• Process Node: 12 nm (2070 SUPER) vs 8 nm (3060 Mobile)
• Foundry: TSMC (2070 SUPER) vs Samsung (3060 Mobile)
• Transistors: 13,600 million (2070 SUPER) vs 12,000 million (3060 Mobile)
• Die Size: 545 mm² (2070 SUPER) vs 276 mm² (3060 Mobile)
• Transistor Density: 25.0M / mm² (2070 SUPER) vs 43.5M / mm² (3060 Mobile)
• Base Clock: 1605 MHz (2070 SUPER) vs 900 MHz (3060 Mobile)
• Boost Clock: 1770 MHz (2070 SUPER) vs 1425 MHz (3060 Mobile)
• Memory Size: 8 GB (2070 SUPER) vs 6 GB (3060 Mobile)
• Memory Bus Width: 256 bit (2070 SUPER) vs 192 bit (3060 Mobile)
• Memory Bandwidth: 448.0 GB/s (2070 SUPER) vs 336.0 GB/s (3060 Mobile)
• Shading Units: 2560 (2070 SUPER) vs 3840 (3060 Mobile)
• TMUs: 160 (2070 SUPER) vs 120 (3060 Mobile)
• ROPs: 64 (2070 SUPER) vs 48 (3060 Mobile)
• RT Cores: 40 (2070 SUPER) vs 30 (3060 Mobile)
• Tensor Cores: 320 (2070 SUPER) vs 120 (3060 Mobile)
• Pixel Rate: 113.3 GPixel/s (2070 SUPER) vs 68.40 GPixel/s (3060 Mobile)
• Texture Rate: 283.2 GTexel/s (2070 SUPER) vs 171.0 GTexel/s (3060 Mobile)
• FP32: 9.062 TFLOPS (2070 SUPER) vs 10.94 TFLOPS (3060 Mobile)
• FP16: 18.12 TFLOPS (2:1) (2070 SUPER) vs 10.94 TFLOPS (1:1) (3060 Mobile)
• TDP: 215 W (2070 SUPER) vs 80 W (3060 Mobile)
• Bus Interface: PCIe 3.0 x16 (2070 SUPER) vs PCIe 4.0 x16 (3060 Mobile)
• Power Connectors: 1x 6-pin + 1x 8-pin (2070 SUPER) vs None (3060 Mobile)
• Suggested PSU: 550 W (2070 SUPER) vs None listed (3060 Mobile)
• Display Outputs: 1x HDMI 2.0, 3x DisplayPort 1.4a, 1x USB Type-C (2070 SUPER) vs Portable Device Dependent (3060 Mobile)
• Dimensions: 267 mm x 116 mm x 35 mm (2070 SUPER) vs not listed (3060 Mobile)
• Release Date: July 8, 2019 (2070 SUPER) vs January 11, 2021 (3060 Mobile)
• Launch MSRP: 499 USD (2070 SUPER) vs not listed (3060 Mobile)