AMD Radeon RX 9070 vs NVIDIA GeForce RTX 3080 Mobile Comparison

Head-to-Head Benchmarks

The benchmark data presents a lopsided contest. The AMD Radeon RX 9070 wins 9 of the 10 head-to-head tests, and the margins are often dramatic. In 3DMark Steel Nomad DX12, the RX 9070 scores 6290 against the RTX 3080 Mobile's 2644 — a 137.9% advantage. That is not a marginal lead; it is a generational gap made visible in a single direct comparison.

The PassMark suite tells the same story. In DirectX 11, the AMD card posts 281 versus 146, a 92.5% win. DirectX 9 shows 343 against 170, a 101.8% lead. The GPU compute test is similarly one-sided: 14737 for AMD versus 7276 for NVIDIA, a 102.5% difference. The RX 9070's nearest-rival data reinforces this: its average benchmark score of 23877 sits 1.1% above the RTX 3080 Mobile's 23628, but that average masks the extreme spread — the AMD card dominates in raw compute while the NVIDIA part claws back one specific API.

The single NVIDIA victory is in Geekbench Vulkan, where the RTX 3080 Mobile scores 104066 against the RX 9070's 58705. That is a 43.6% swing in the opposite direction. It is an outlier, but a significant one — it suggests the NVIDIA driver stack handles that particular workload far better, and it prevents the comparison from being a total shutout.

Geekbench OpenCL is closer but still firmly AMD: 131539 versus 104831, a 25.5% win. PassMark G3D gives the RX 9070 a 55.5% lead (25381 vs 16321). Even the 2D test, where both cards are far from their compute peaks, shows the AMD part at 1280 versus 637 — a 100.9% margin. The smallest win is DirectX 12, where the RX 9070's 74 barely edges out 72, a 2.8% difference. That near-tie in modern API performance is worth noting, but it does not offset the scale of the other losses.

Architecture Differences

The two GPUs come from different foundries and different design philosophies. The RX 9070 uses the Navi 48 chip built on TSMC's 4 nm process, with 53,900 million transistors packed into a 357 mm² die. That yields a transistor density of 151.0 million per mm². The RTX 3080 Mobile uses the GA104 chip on Samsung's 8 nm node, with just 17,400 million transistors on a larger 392 mm² die — a density of 44.4 million per mm². The process advantage is stark: the AMD card crams more than three times the transistors into a smaller area.

Clock speeds reflect that efficiency. The RX 9070 runs at a 1330 MHz base and 2520 MHz boost, with a game clock of 2070 MHz. The RTX 3080 Mobile is far more conservative: 1110 MHz base and 1545 MHz boost. That clock gap, combined with the architectural differences, explains much of the compute delta. The AMD card's FP32 throughput is 36.13 TFLOPS; the NVIDIA part manages 18.98 TFLOPS. Both claim 1:1 FP16, but the raw numbers are not close.

Memory is another differentiator. The RX 9070 carries 16 GB of GDDR6 on a 256-bit bus at 2518 MHz (20.1 Gbps effective), delivering 644.6 GB/s of bandwidth. The RTX 3080 Mobile has 8 GB of GDDR6 on the same 256-bit bus but at 1750 MHz (14 Gbps effective), for 448.0 GB/s. That is a 43.9% bandwidth advantage for AMD, and double the capacity. Rasterization resources also favor AMD: 3584 shading units, 224 TMUs, and 128 ROPs versus NVIDIA's 6144 shading units, 192 TMUs, and 96 ROPs. The NVIDIA part has more ALUs but fewer texture units and ROPs, and its lower clocks cap its realized output.

Ray tracing hardware differs too. The RX 9070 has 56 RT cores; the RTX 3080 Mobile has 48 RT cores but adds 192 tensor cores, which the AMD part lacks entirely. The NVIDIA card's pixel rate is 148.3 GPixel/s and texture rate is 296.6 GTexel/s; the RX 9070 hits 322.6 GPixel/s and 564.5 GTexel/s. The RX 9070 is a desktop card with a 220 W TDP, dual-slot cooler, and 2x 8-pin power connectors, plus a 550 W suggested PSU. The RTX 3080 Mobile is a 115 W laptop part with no power connectors and display outputs described as "Portable Device Dependent." The RX 9070 uses PCIe 5.0 x16; the mobile part uses PCIe 4.0 x16.

FAQ

Q: Which GPU wins the most benchmarks overall?

A: The AMD Radeon RX 9070 wins 9 of the 10 head-to-head tests. The only exception is Geekbench Vulkan, where the NVIDIA GeForce RTX 3080 Mobile leads by 43.6%.

Q: How large is the performance gap in the flagship 3DMark test?

A: In 3DMark Steel Nomad DX12, the RX 9070 scores 6290 versus the RTX 3080 Mobile's 2644, a 137.9% difference. This is the largest single-test margin in the comparison.

Q: Is the RTX 3080 Mobile competitive in any compute workload?

A: In Geekbench Vulkan, the RTX 3080 Mobile scores 104066 compared to the RX 9070's 58705. That is a 43.6% win for NVIDIA. In OpenCL, however, the RX 9070 leads by 25.5%.

Q: What is the memory capacity difference?

A: The RX 9070 has 16 GB of GDDR6, while the RTX 3080 Mobile has 8 GB. Both use a 256-bit bus, but the RX 9070's memory runs at 2518 MHz (20.1 Gbps effective) versus 1750 MHz (14 Gbps effective), giving it 644.6 GB/s versus 448.0 GB/s.

Q: How do the two compare in terms of power requirements?

A: The RX 9070 has a 220 W TDP and requires 2x 8-pin power connectors with a 550 W suggested PSU. The RTX 3080 Mobile has a 115 W TDP and uses no power connectors, as it is a portable device part.

Q: Are both cards using the same manufacturing process?

A: No. The RX 9070 uses TSMC's 4 nm process with a 357 mm² die and 53,900 million transistors. The RTX 3080 Mobile uses Samsung's 8 nm process with a 392 mm² die and 17,400 million transistors.

The Verdict

The data is unambiguous. The AMD Radeon RX 9070 is the faster GPU in nearly every measurable way. Its average benchmark score of 23877 sits 1.1% above the RTX 3080 Mobile's 23628, but the head-to-head results show the average flatters the NVIDIA part. In raw compute, rasterization, and memory bandwidth, the RX 9070 is ahead by margins ranging from 2.8% to 137.9%. The RTX 3080 Mobile's lone Vulkan win is real but isolated.

That said, context matters. The RX 9070 is a desktop card with a 220 W TDP, a dual-slot cooler, and a launch MSRP of 549 USD. The RTX 3080 Mobile is a laptop part with a 115 W TDP and no discrete power connectors. These are not competing in the same chassis. The RX 9070 is a current-generation product, released on 2025-03-05, and still in active production. The RTX 3080 Mobile launched on 2021-01-11 and is end-of-life. The 4 nm node versus 8 nm node difference is not academic — it explains the clock and efficiency gap.

For a builder choosing between these two, the answer depends entirely on the form factor. If you need a mobile GPU, the RTX 3080 Mobile is the only option here — the RX 9070 cannot fit in a laptop. If you are building a desktop, the RX 9070 is the clear choice on performance, with 16 GB of memory versus 8 GB, and a 644.6 GB/s bandwidth advantage. The RTX 3080 Mobile's 192 tensor cores are its only hardware feature the AMD card lacks, but no benchmark in the data shows that translating into a win outside of Vulkan.

Specification Differences

The two cards differ in nearly every major specification category. The RX 9070 uses a 4 nm TSMC process; the RTX 3080 Mobile uses 8 nm Samsung. Transistor counts are 53,900 million versus 17,400 million, on die sizes of 357 mm² versus 392 mm². Density is 151.0M/mm² versus 44.4M/mm². Base clocks are 1330 MHz versus 1110 MHz; boost clocks are 2520 MHz versus 1545 MHz. The RX 9070 also lists a game clock of 2070 MHz, which the RTX 3080 Mobile does not have.

Memory differs in size and speed: 16 GB versus 8 GB, with 2518 MHz (20.1 Gbps effective) versus 1750 MHz (14 Gbps effective). Bandwidth is 644.6 GB/s versus 448.0 GB/s. Shading units favor NVIDIA at 6144 versus 3584, but TMUs favor AMD at 224 versus 192, and ROPs favor AMD at 128 versus 96. RT core counts are 56 versus 48; tensor cores exist only on the NVIDIA part (192). Pixel rate is 322.6 GPixel/s versus 148.3 GPixel/s; texture rate is 564.5 GTexel/s versus 296.6 GTexel/s. FP32 is 36.13 TFLOPS versus 18.98 TFLOPS.

Power and physical specs differ sharply. The RX 9070 has a 220 W TDP, dual-slot width, 2x 8-pin connectors, and a 550 W suggested PSU. The RTX 3080 Mobile has a 115 W TDP, no slot width listed, no power connectors, and no suggested PSU. Bus interfaces are PCIe 5.0 x16 versus PCIe 4.0 x16. Display outputs are 1x HDMI 2.1b and 3x DisplayPort 2.1a for AMD, versus "Portable Device Dependent" for NVIDIA. Production status is Active versus End-of-life. Release dates are 2025-03-05 versus 2021-01-11. The RX 9070 has a launch MSRP of 549 USD; the RTX 3080 Mobile has none listed.

Where Each One Wins

The RX 9070 wins in every scenario that relies on raw throughput, memory bandwidth, or modern API performance. Its 137.9% lead in 3DMark Steel Nomad DX12 makes it the choice for high-fidelity DX12 gaming. The 92.5% DirectX 11 and 101.8% DirectX 9 wins cover older titles. The 102.5% GPU compute lead and 25.5% OpenCL advantage make it the pick for compute-heavy workloads like rendering or general GPU computing. The 100.9% G2D win is less relevant to gaming but shows it is not a slouch in 2D tasks either. Its 16 GB memory capacity and 644.6 GB/s bandwidth position it for high-resolution textures and large datasets.

The RTX 3080 Mobile wins exactly one benchmark: Geekbench Vulkan, by 43.6%. That makes it the better choice for Vulkan-specific applications or games that heavily leverage that API. Its 192 tensor cores, which the RX 9070 lacks entirely, suggest an advantage in AI-related workloads, though no benchmark in the data directly measures that. Its 115 W TDP means it is the only one of the two that can exist in a laptop form factor, and it does so without external power connectors.

The practical split is form-factor driven. For a desktop build where power and cooling are available, the RX 9070 wins on nearly every metric and is the obvious pick. For a mobile system, the RTX 3080 Mobile is the only option, and its Vulkan strength is a genuine bright spot. If you are deciding between these two in a vacuum, the RX 9070 is the superior GPU — but the RTX 3080 Mobile holds a niche in portable systems and Vulkan-heavy workloads.