NVIDIA GeForce RTX 2070 SUPER vs NVIDIA RTX A4000 Mobile Comparison

The benchmark data presents a clear split: the NVIDIA RTX A4000 Mobile wins in OpenCL compute, while the NVIDIA GeForce RTX 2070 SUPER dominates in every other head-to-head test, including all DirectX and Vulkan workloads. The A4000 Mobile secures 1 win out of 9 comparisons, with an 8-win margin for the 2070 SUPER. This is not a close contest overall; it is a decisive victory for the older desktop card in gaming and graphics API performance, despite the A4000 Mobile being a newer, more efficient mobile workstation part.

The Verdict

From the data, the NVIDIA GeForce RTX 2070 SUPER is the clear performance pick for anyone prioritizing raw graphics throughput. It leads in PassMark G3D (18169 vs 14796, an 18.6% advantage), Vulkan (90637 vs 73002, a 19.5% advantage), and every legacy DirectX test, from DirectX 9 (223 vs 157) to DirectX 12 (67 vs 66). The 2070 SUPER also holds a 15.4% lead in PassMark GPU compute (7557 vs 6394). Its average benchmark score of 20282 places it in the 65th percentile of all GPUs, while the A4000 Mobile’s average of 21379 puts it in the 66th percentile—a negligible overall difference that masks the lopsided head-to-head results.

The NVIDIA RTX A4000 Mobile, however, is not without its own justification. Its sole victory is in Geekbench OpenCL, where it scores 97178 against 83358, a 16.6% margin. This suggests a specific strength in compute-heavy, non-graphics workloads. For a mobile workstation, this could be the more relevant metric. The A4000 Mobile also achieves this with a 115 W TDP compared to the 2070 SUPER’s 215 W, making it the more power-efficient choice. The data shows the 2070 SUPER is for those who want maximum graphics and gaming performance; the A4000 Mobile is for users whose primary workload is OpenCL compute and who need a lower power envelope in a portable form factor.

Architecture Differences

The two cards are built on fundamentally different architectures and processes. The RTX A4000 Mobile uses the GA104 chip on the Ampere architecture, fabricated on an 8 nm process by Samsung. It packs 17,400 million transistors into a 392 mm² die, yielding a transistor density of 44.4M per mm². In contrast, the RTX 2070 SUPER uses the TU104 chip on the older Turing architecture, built on TSMC’s 12 nm process. It contains 13,600 million transistors on a much larger 545 mm² die, with a density of just 25.0M per mm². This means the A4000 Mobile fits more transistors into a smaller space, a direct result of the more advanced process node.

The A4000 Mobile also doubles the shading units (5120 vs 2560) and has more ROPs (80 vs 64), though both have 160 TMUs. This explains its much higher FP32 throughput of 17.20 TFLOPS versus the 2070 SUPER’s 9.062 TFLOPS. Interestingly, the 2070 SUPER has double the tensor cores (320 vs 160) and offers FP16 performance at a 2:1 ratio (18.12 TFLOPS), while the A4000 Mobile runs FP16 at a 1:1 ratio (17.20 TFLOPS). Ray tracing hardware is identical at 40 RT cores per card. The A4000 Mobile also uses a PCIe 4.0 x16 interface, while the 2070 SUPER is limited to PCIe 3.0 x16. The A4000 Mobile’s memory runs at 12 Gbps effective, while the 2070 SUPER’s GDDR6 is faster at 14 Gbps effective, giving the older card a bandwidth advantage of 448.0 GB/s versus 384.0 GB/s.

FAQ

Q: Which card has a higher average benchmark score?

A: The NVIDIA RTX A4000 Mobile has a higher average benchmark score of 21379, compared to the NVIDIA GeForce RTX 2070 SUPER’s 20282. This places the A4000 Mobile in the 66th percentile and the 2070 SUPER in the 65th percentile of all GPUs.

Q: In which benchmark does the RTX A4000 Mobile beat the RTX 2070 SUPER?

A: The A4000 Mobile wins only in Geekbench OpenCL, scoring 97178 versus 83358, a 16.6% advantage. It loses all other head-to-head tests.

Q: What is the TDP difference between the two cards?

A: The RTX A4000 Mobile has a TDP of 115 W, while the RTX 2070 SUPER has a TDP of 215 W. The A4000 Mobile is the lower-power part by a significant margin.

Q: How does the memory bandwidth compare?

A: The RTX 2070 SUPER has higher memory bandwidth at 448.0 GB/s, compared to the RTX A4000 Mobile’s 384.0 GB/s. Both use 8 GB of GDDR6 memory on a 256-bit bus, but the 2070 SUPER’s memory runs at 14 Gbps effective versus 12 Gbps effective.

Q: Which card has more shading units?

A: The RTX A4000 Mobile has 5120 shading units, which is double the RTX 2070 SUPER’s 2560. This contributes to its higher FP32 compute performance of 17.20 TFLOPS versus 9.062 TFLOPS.

Q: Are both cards end-of-life products?

A: Yes, both the NVIDIA RTX A4000 Mobile and the NVIDIA GeForce RTX 2070 SUPER are listed with a production status of "End-of-life."

Specification Differences

The two cards differ across nearly every core specification. The RTX A4000 Mobile uses a GA104 chip on an 8 nm Samsung process, while the RTX 2070 SUPER uses a TU104 chip on a 12 nm TSMC process. The A4000 Mobile has 17,400 million transistors on a 392 mm² die, while the 2070 SUPER has 13,600 million transistors on a 545 mm² die. Clock speeds also differ: the A4000 Mobile has a base clock of 1140 MHz and a boost of 1680 MHz, while the 2070 SUPER runs at a 1605 MHz base and 1770 MHz boost.

The memory subsystem shows a split: both have 8 GB GDDR6 on a 256-bit bus, but the A4000 Mobile’s memory is rated at 1500 MHz (12 Gbps effective) with a bandwidth of 384.0 GB/s, while the 2070 SUPER’s memory runs at 1750 MHz (14 Gbps effective) with a bandwidth of 448.0 GB/s. Compute resources differ significantly: the A4000 Mobile has 5120 shading units, 160 TMUs, 80 ROPs, 40 RT cores, and 160 tensor cores; the 2070 SUPER has 2560 shading units, 160 TMUs, 64 ROPs, 40 RT cores, and 320 tensor cores. The A4000 Mobile’s pixel rate is 134.4 GPixel/s versus 113.3 GPixel/s, but its texture rate is lower at 268.8 GTexel/s versus 283.2 GTexel/s.

Power and physical specs diverge strongly. The A4000 Mobile has a 115 W TDP, no power connectors, and a PCIe 4.0 x16 bus interface. The 2070 SUPER has a 215 W TDP, requires 1x 6-pin and 1x 8-pin power connectors, and uses PCIe 3.0 x16. The 2070 SUPER is a dual-slot card measuring 267 mm in length, 116 mm in height, and 35 mm in width, while the A4000 Mobile’s dimensions are listed as portable-device dependent. The 2070 SUPER offers display outputs of 1x HDMI 2.0, 3x DisplayPort 1.4a, and 1x USB Type-C; the A4000 Mobile’s outputs are also portable-device dependent. The 2070 SUPER has a launch MSRP of 499 USD; the A4000 Mobile has no listed launch MSRP.

Head-to-Head Benchmarks

The Geekbench OpenCL result is the A4000 Mobile’s standout performance, delivering a score of 97178 against the 2070 SUPER’s 83358. That is a 16.6% win and the only test where the mobile workstation card comes out ahead. It aligns with the A4000 Mobile’s doubled shading units and higher FP32 throughput, suggesting its compute architecture is better suited to OpenCL’s execution model.

The 2070 SUPER’s wins are broad and often decisive. In Geekbench Vulkan, the 2070 SUPER scores 90637 versus 73002, a 19.5% advantage. This is notable because the A4000 Mobile is a newer architecture, yet the older card still wins by a wide margin in this modern graphics API. The PassMark G3D test reinforces this trend, with the 2070 SUPER scoring 18169 against 14796, an 18.6% lead. This is the most direct measure of overall 3D graphics performance, and the result is unambiguous.

The legacy DirectX tests favor the 2070 SUPER even more heavily. In PassMark DirectX 9, the 2070 SUPER scores 223 versus 157, a 29.6% advantage—the largest delta in the entire comparison. In DirectX 10, the 2070 SUPER wins 132 to 105, a 20.5% lead. DirectX 11 shows a 15.9% advantage (151 vs 127), and even DirectX 12, where the scores are closest, the 2070 SUPER edges out a win at 67 versus 66, a 1.5% margin. The 2070 SUPER also wins the 2D and compute tests: PassMark G2D at 878 versus 585 (33.4% lead) and PassMark GPU compute at 7557 versus 6394 (15.4% lead). The pattern is consistent: the only test where the A4000 Mobile’s newer architecture and higher compute specs translate to a win is OpenCL, while the 2070 SUPER’s higher clocks and memory bandwidth deliver superior results in every graphics and legacy API workload.