NVIDIA GeForce RTX 3080 Ti vs NVIDIA GeForce RTX 4090 Mobile Comparison

The data presents a clear split: the NVIDIA GeForce RTX 4090 Mobile and the NVIDIA GeForce RTX 3080 Ti are closely matched in overall average score, but they achieve that parity through very different strengths. The 4090 Mobile edges out the 3080 Ti in overall average benchmark score (43667 vs 41187) and holds a higher percentile rank (84th vs 83rd), but the 3080 Ti wins more individual head-to-head tests (5 vs 4). The verdict is nuanced: the 4090 Mobile is the superior choice for modern DirectX 11 and DirectX 9 workloads, while the 3080 Ti is the pick for compute-heavy tasks and Vulkan applications, with the 4090 Mobile's advantage in the newer 3DMark Steel Nomad test (5077 vs the 3080 Ti's absent score) signaling better future-proofing for next-generation APIs.

The Verdict

The benchmark results indicate that the NVIDIA GeForce RTX 4090 Mobile is the overall winner, but by a slim margin. Its average benchmark score of 43667 is 6% higher than the 3080 Ti's 41187, and it sits at the 84th percentile of all GPUs compared to the 3080 Ti's 83rd. This makes the 4090 Mobile the better all-rounder for gaming and general graphics, particularly in DirectX 11 titles where it leads by 17.5% (262 vs 223) and DirectX 9 where it leads by 13.1% (310 vs 274).

However, the NVIDIA GeForce RTX 3080 Ti is not obsolete. For users prioritizing raw compute throughput, the 3080 Ti dominates the Passmark GPU Compute test by a massive 19.2% (15282 vs 12347). It also wins the Vulkan benchmark by 11.4% (192697 vs 170774), making it the better option for Vulkan-based games and compute workloads. The 3080 Ti's higher FP32 performance (34.10 TFLOPS vs 32.98 TFLOPS) aligns with its compute win. The choice depends on the primary workload: the 4090 Mobile for balanced gaming, the 3080 Ti for compute and Vulkan.

Architecture Differences

The two GPUs represent distinct architectural generations from NVIDIA. The RTX 4090 Mobile is built on the Ada Lovelace architecture using the AD103 chip, fabricated on a 5 nm process at TSMC. In contrast, the RTX 3080 Ti uses the Ampere architecture with the GA102 chip, built on an 8 nm process at Samsung. This process difference is stark: the 4090 Mobile packs 45,900 million transistors into a 379 mm² die, achieving a transistor density of 121.1M / mm², while the 3080 Ti has 28,300 million transistors on a much larger 628 mm² die, with a density of only 45.1M / mm². The 4090 Mobile's newer node is far more efficient in transistor packing.

Memory configurations also differ fundamentally. The 4090 Mobile uses 16 GB of GDDR6 on a 256-bit bus, delivering 576.0 GB/s of bandwidth. The 3080 Ti uses 12 GB of GDDR6X on a wider 384-bit bus, achieving a significantly higher 912.4 GB/s bandwidth. The 3080 Ti's memory is faster in raw throughput, but the 4090 Mobile offers more capacity. Core counts are similar in shading units (9728 vs 10240) and TMUs (304 vs 320), but the 4090 Mobile has fewer RT cores (76 vs 80) and tensor cores (304 vs 320). Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Head-to-Head Benchmarks

Walking through the individual benchmark results shows a clear pattern of specialization. The RTX 4090 Mobile's biggest win is in Passmark DirectX 11, where it scores 262 versus the 3080 Ti's 223, a 17.5% advantage. It also takes Passmark DirectX 9 with 310 versus 274 (13.1% ahead). In Geekbench OpenCL, the 4090 Mobile leads with 180831 versus 170037, a 6.3% win. Its narrowest victory is in Passmark G3D, where it scores 27212 versus 26896, just 1.2% ahead.

The RTX 3080 Ti counters with dominant wins in compute and modern API tests. Its largest victory is in Passmark GPU Compute, scoring 15282 versus 12347, a 19.2% margin. In Geekbench Vulkan, it scores 192697 versus 170774, an 11.4% lead. It also wins Passmark G2D (1091 vs 984, 9.8% ahead), Passmark DirectX 10 (184 vs 173, 6% ahead), and Passmark DirectX 12 (110 vs 107, 2.7% ahead). Notably, the 3080 Ti has a 3DMark Steel Nomad DX12 score of 5077, a test the 4090 Mobile does not have data for. The 4090 Mobile's wins are in older DirectX APIs, while the 3080 Ti excels in compute and Vulkan.

Specification Differences

The specification sheets reveal several key differences beyond architecture and memory.

• Process Node: 5 nm (TSMC) for the 4090 Mobile vs 8 nm (Samsung) for the 3080 Ti.
• Transistors: 45,900 million vs 28,300 million.
• Die Size: 379 mm² vs 628 mm².
• Transistor Density: 121.1M / mm² vs 45.1M / mm².
• Base Clock: 1335 MHz vs 1365 MHz.
• Boost Clock: 1695 MHz vs 1665 MHz.
• Memory Clock: 2250 MHz (18 Gbps effective) vs 1188 MHz (19 Gbps effective).
• Memory Size: 16 GB vs 12 GB.
• Memory Type: GDDR6 vs GDDR6X.
• Memory Bus Width: 256 bit vs 384 bit.
• Memory Bandwidth: 576.0 GB/s vs 912.4 GB/s.
• Shading Units: 9728 vs 10240.
• TMUs: 304 vs 320.
• ROPs: 112 vs 112 (same).
• RT Cores: 76 vs 80.
• Tensor Cores: 304 vs 320.
• Pixel Rate: 189.8 GPixel/s vs 186.5 GPixel/s.
• Texture Rate: 515.3 GTexel/s vs 532.8 GTexel/s.
• FP32 Performance: 32.98 TFLOPS vs 34.10 TFLOPS.
• TDP: 120 W vs 350 W.
• Slot Width: IGP vs Dual-slot.
• Power Connectors: None vs 1x 12-pin.
• Suggested PSU: None vs 750 W.
• Display Outputs: Portable Device Dependent vs 1x HDMI 2.1, 3x DisplayPort 1.4a.
• Dimensions: Not listed vs 285 mm (11.2 inches) length, 112 mm (4.4 inches) height, 40 mm (1.6 inches) width.
• Production Status: Active vs End-of-life.
• Release Date: 2023-01-02 vs 2021-05-30.
• Launch MSRP: The 3080 Ti has a launch MSRP of 1,199 USD; the 4090 Mobile has no listed MSRP.

The 4090 Mobile is a mobile IGP with no power connectors, while the 3080 Ti is a dual-slot desktop card requiring a 750 W PSU.

FAQ

Q: Which GPU has a higher average benchmark score?

A: The NVIDIA GeForce RTX 4090 Mobile has a higher average benchmark score of 43667, compared to the RTX 3080 Ti's 41187.

Q: Which GPU wins the Vulkan benchmark?

A: The NVIDIA GeForce RTX 3080 Ti wins the Geekbench Vulkan test with a score of 192697, which is 11.4% higher than the RTX 4090 Mobile's 170774.

Q: How much faster is the RTX 4090 Mobile in DirectX 11?

A: The RTX 4090 Mobile scores 262 in Passmark DirectX 11, which is 17.5% higher than the RTX 3080 Ti's 223.

Q: Which GPU has more memory bandwidth?

A: The NVIDIA GeForce RTX 3080 Ti has significantly more memory bandwidth at 912.4 GB/s, compared to the RTX 4090 Mobile's 576.0 GB/s.

Q: What is the TDP of each GPU?

A: The RTX 4090 Mobile has a TDP of 120 W, while the RTX 3080 Ti has a TDP of 350 W.

Q: Which GPU is better for compute workloads?

A: The RTX 3080 Ti is better for compute, winning the Passmark GPU Compute test by 19.2% (15282 vs 12347) and having a higher FP32 performance of 34.10 TFLOPS.

Where Each One Wins

The NVIDIA GeForce RTX 4090 Mobile is the winner for users focused on legacy DirectX gaming and balanced performance. Its wins in DirectX 11 (17.5% ahead) and DirectX 9 (13.1% ahead) make it the better choice for older game titles that rely on these APIs. Its higher average score (43667) and 84th percentile ranking also make it the better all-around GPU for mixed workloads. The 4090 Mobile's active production status and newer release date (2023-01-02) suggest it is the current-generation option, with a lower TDP of 120 W making it suitable for mobile form factors.

The NVIDIA GeForce RTX 3080 Ti is the winner for compute-intensive tasks and Vulkan-based applications. Its 19.2% lead in Passmark GPU Compute (15282 vs 12347) and 11.4% lead in Vulkan (192697 vs 170774) are decisive. Its higher memory bandwidth (912.4 GB/s) and FP32 performance (34.10 TFLOPS) support these compute wins. It also wins in DirectX 12 by 2.7% and DirectX 10 by 6%, making it competitive in modern APIs. The 3080 Ti's dedicated desktop form factor, with dual-slot cooling and display outputs, makes it the choice for a stationary workstation. Its presence in the 3DMark Steel Nomad DX12 test (5077) suggests data exists for the newest API, though the 4090 Mobile's lack of a score there is notable. For raw compute and Vulkan, the 3080 Ti is the superior pick.