NVIDIA GeForce RTX 2080 vs NVIDIA GeForce RTX 3080 Mobile Comparison

The NVIDIA GeForce RTX 3080 Mobile and the NVIDIA GeForce RTX 2080 represent two distinct generations of NVIDIA graphics technology, with the former being a mobile-first implementation of the Ampere architecture and the latter a desktop Turing-based card. The benchmark data reveals a complex rivalry where the newer mobile chip wins decisively in modern DirectX 12 workloads, while the older desktop card maintains advantages in several legacy and compute-oriented tests. This analysis explores the head-to-head results, architectural implications, and the practical strengths of each GPU based strictly on the provided data.

Head-to-Head Benchmarks

The most striking result in the comparison is the 3DMark Steel Nomad DX12 test, where the RTX 3080 Mobile scores 2644 against the RTX 2080’s 1752. This represents a massive 50.9% victory for the mobile part, indicating a substantial lead in modern, graphics-intensive API workloads. This single result suggests the Ampere architecture’s improvements in geometry processing and ray tracing capabilities are highly effective in current-generation game engines.

The Geekbench OpenCL test also favors the RTX 3080 Mobile, with a score of 104831 compared to 91313 for the RTX 2080. This 14.8% advantage in a general-purpose compute benchmark highlights the raw processing throughput advantage of the newer chip, which is likely driven by its significantly higher FP32 performance. The mobile GPU’s lead here shows that despite its lower thermal envelope, its architectural efficiency allows it to outperform the older desktop card in raw number crunching.

However, the RTX 2080 fights back in several areas. The Geekbench Vulkan test shows the desktop card winning with a score of 107797 versus 104066 for the RTX 3080 Mobile, a 3.5% margin. This suggests that in Vulkan-specific workloads, the RTX 2080’s higher clock speeds and potentially more mature driver optimizations for that API give it an edge, even though the RTX 3080 Mobile has a newer architecture. The delta is small, but it demonstrates that API-level optimizations can still favor the older design.

The Passmark suite paints a more complex picture. In DirectX 10 and DirectX 11 tests, the RTX 2080 wins with scores of 136 and 158, respectively, against the RTX 3080 Mobile’s 120 and 146. These are 11.8% and 7.6% victories for the desktop card. The DirectX 9 test shows an even larger gap, with the RTX 2080 scoring 223 against 170 for the RTX 3080 Mobile, a 23.8% difference. This pattern suggests that the older Turing architecture retains strong performance in legacy DirectX pipelines, possibly due to higher base and boost clocks that are less impacted by thermal constraints in a desktop form factor.

In the Passmark G3D test, which is a general gaming-oriented benchmark, the RTX 2080 wins with 18720 points versus 16321 for the RTX 3080 Mobile, a 12.8% lead. This is a notable result because it suggests that in mixed or older game workloads, the desktop card’s sustained performance is superior. The Passmark G2D test also goes to the RTX 2080 with 907 points against 637, a 29.8% margin, likely reflecting the desktop card’s dedicated display outputs and potentially better 2D acceleration paths.

The Passmark GPU Compute test shows the RTX 2080 winning with 7872 against 7276, a 7.6% advantage. This is interesting because it contradicts the Geekbench OpenCL result, suggesting that the two benchmarks stress different aspects of compute performance, with the RTX 2080 potentially benefiting from its higher TDP and sustained clock speeds. The DirectX 12 Passmark test is a tie at 72 points each, indicating parity in that specific workload. Overall, the RTX 2080 wins 7 out of 10 head-to-head tests, but the RTX 3080 Mobile wins the most demanding modern benchmark by a landslide.

Architecture Differences

The fundamental architectural split is between Ampere and Turing. The RTX 3080 Mobile uses the GA104 chip on an 8 nm Samsung process, while the RTX 2080 uses the TU104 chip on a 12 nm TSMC process. This process advantage allows the mobile chip to pack 17,400 million transistors into a 392 mm² die, resulting in a transistor density of 44.4M / mm². In contrast, the RTX 2080 has 13,600 million transistors on a much larger 545 mm² die, with a density of just 25.0M / mm². This density difference explains how the RTX 3080 Mobile can achieve higher performance in a smaller, more power-efficient package.

The compute resource allocation differs dramatically. The RTX 3080 Mobile features 6144 shading units, 192 TMUs, and 96 ROPs, while the RTX 2080 has 2944 shading units, 184 TMUs, and 64 ROPs. The mobile chip has more than double the shading units, which directly contributes to its higher FP32 throughput of 18.98 TFLOPS versus 10.07 TFLOPS for the RTX 2080. However, the RTX 2080 has a higher FP16 performance of 20.14 TFLOPS with a 2:1 ratio, compared to the RTX 3080 Mobile’s 18.98 TFLOPS with a 1:1 ratio. This suggests the Turing card was designed with different mixed-precision compute priorities.

Ray tracing and tensor core configurations also differ. The RTX 3080 Mobile has 48 RT cores and 192 tensor cores, while the RTX 2080 has 46 RT cores and 368 tensor cores. The mobile chip has more RT cores but significantly fewer tensor cores, which could impact AI-accelerated workloads like DLSS. The memory subsystems are identical in capacity and bandwidth, with both using 8 GB of GDDR6 on a 256-bit bus delivering 448.0 GB/s, but the clock speeds and bus interface differ, with the RTX 3080 Mobile using PCIe 4.0 x16 and the RTX 2080 using PCIe 3.0 x16.

The power and physical characteristics are starkly different. The RTX 3080 Mobile has a TDP of 115 W and no power connectors, as it is designed for portable devices. The RTX 2080 has a 215 W TDP, requires a 1x 6-pin + 1x 8-pin power connector, and is a dual-slot card measuring 267 mm in length. This highlights the fundamental design goal of each: the mobile chip prioritizes efficiency and portability, while the desktop card prioritizes raw sustained performance with generous power delivery.

FAQ

Q: Which GPU is faster in modern DirectX 12 games?

A: The RTX 3080 Mobile is decisively faster in the 3DMark Steel Nomad DX12 test, scoring 2644 versus 1752 for the RTX 2080, a 50.9% advantage. This indicates a clear lead in modern graphics workloads.

Q: Does the RTX 2080 win any benchmarks?

A: Yes, the RTX 2080 wins 7 out of 10 head-to-head tests, including Geekbench Vulkan, Passmark DirectX 9/10/11, Passmark G2D, Passmark G3D, and Passmark GPU Compute. Its largest win is in Passmark G2D with a 29.8% margin.

Q: How do their compute performances compare?

A: The results are mixed. The RTX 3080 Mobile wins Geekbench OpenCL with 104831 points versus 91313, a 14.8% lead. However, the RTX 2080 wins Passmark GPU Compute with 7872 points versus 7276, a 7.6% advantage.

Q: What is the most significant architectural difference?

A: The RTX 3080 Mobile uses the Ampere architecture on an 8 nm Samsung process with 6144 shading units, while the RTX 2080 uses Turing on a 12 nm TSMC process with 2944 shading units. This leads to a large difference in FP32 performance.

Q: Do both GPUs have the same memory configuration?

A: Yes, both have 8 GB of GDDR6 memory on a 256-bit bus with 448.0 GB/s bandwidth. However, they use different PCIe interfaces, with the RTX 3080 Mobile using PCIe 4.0 x16 and the RTX 2080 using PCIe 3.0 x16.

Q: Which GPU has a higher power requirement?

A: The RTX 2080 has a TDP of 215 W and requires a 550 W suggested PSU, while the RTX 3080 Mobile has a TDP of 115 W and no power connectors, reflecting its mobile design.

Specification Differences

The primary specification differences are numerous. The process node differs, with the RTX 3080 Mobile on 8 nm versus the RTX 2080 on 12 nm. The transistor count is 17,400 million versus 13,600 million, and the die size is 392 mm² versus 545 mm². The shading units are 6144 versus 2944, TMUs are 192 versus 184, and ROPs are 96 versus 64. RT cores are 48 versus 46, while tensor cores are 192 versus 368.

Clock speeds also differ: the RTX 3080 Mobile has a base clock of 1110 MHz and a boost of 1545 MHz, while the RTX 2080 has a base of 1515 MHz and a boost of 1710 MHz. The FP32 performance is 18.98 TFLOPS versus 10.07 TFLOPS, and FP16 is 18.98 TFLOPS (1:1) versus 20.14 TFLOPS (2:1). The pixel rate is 148.3 GPixel/s versus 109.4 GPixel/s, but the texture rate is 296.6 GTexel/s versus 314.6 GTexel/s. The TDP is 115 W versus 215 W.

The bus interface is PCIe 4.0 x16 versus PCIe 3.0 x16. The RTX 2080 has defined display outputs (1x HDMI 2.0, 3x DisplayPort 1.4a, 1x USB Type-C), while the RTX 3080 Mobile’s outputs are portable device dependent. The RTX 2080 is a dual-slot card with dimensions of 267 mm x 116 mm x 35 mm, while the RTX 3080 Mobile has no specified dimensions. The RTX 2080 has a launch MSRP of 699 USD, while the RTX 3080 Mobile has none listed.

The Verdict

The data presents a nuanced verdict. The RTX 3080 Mobile is the clear winner for modern, API-heavy workloads, as evidenced by its 50.9% lead in 3DMark Steel Nomad DX12 and 14.8% lead in Geekbench OpenCL. Its architectural advantages in shading units and FP32 throughput make it the superior choice for future-proof gaming and compute tasks. The RTX 2080, however, remains competitive in legacy DirectX tests and general compute benchmarks, winning the Passmark G3D test by 12.8% and the G2D test by 29.8%. Its higher clock speeds and sustained desktop power delivery allow it to excel in older titles and certain compute scenarios.

For a user prioritizing modern game performance and efficiency, the RTX 3080 Mobile is the recommended choice. Its performance in the most demanding benchmark suggests it will handle upcoming titles better. For users with a library of older DirectX 9-11 games or specific compute workloads that favor the Turing architecture, the RTX 2080 still holds value. The tie in Passmark DirectX 12 further complicates the picture, indicating that not all modern APIs show the same gap.

Where Each One Wins

NVIDIA GeForce RTX 3080 Mobile wins in:

• Modern DirectX 12 gaming: The 50.9% lead in 3DMark Steel Nomad DX12 is its most dominant result, indicating a strong advantage in current-generation game engines.
• General OpenCL compute: A 14.8% win in Geekbench OpenCL shows it is more capable in cross-platform compute tasks.
• Efficiency and portability: With a 115 W TDP and no power connectors, it is designed for thin-and-light laptops, trading raw sustained performance for mobility.

NVIDIA GeForce RTX 2080 wins in:

• Legacy DirectX performance: Wins in DirectX 9 (by 23.8%), DirectX 10 (by 11.8%), and DirectX 11 (by 7.6%) make it better for older game libraries.
• 2D and general graphics: A 29.8% lead in Passmark G2D and a 12.8% lead in Passmark G3D suggest it handles mixed workloads more consistently.
• Specific compute benchmarks: A 7.6% win in Passmark GPU Compute indicates that some compute workloads still favor its higher clock speeds and 2:1 FP16 ratio.
• Vulkan API: A 3.5% win in Geekbench Vulkan shows it can outperform the newer chip in that specific API context.