AMD Radeon RX 9060 XT 16 GB vs NVIDIA GeForce 930A Comparison

The NVIDIA GeForce 930A and AMD Radeon RX 9060 XT 16 GB are separated by a decade of GPU architecture, and the benchmark data reflects that gulf. The 930A, a Maxwell-era part from 2015, records a single OpenCL score of 5317, placing it in the 31st percentile of all GPUs. The RX 9060 XT, an RDNA 4.0 part from 2025, posts a much wider benchmark profile, with its highest scores in DirectX workloads and compute, though its average benchmark score of 4657 and 27th percentile ranking are dragged down by several low DirectX legacy results.

Head-to-Head Benchmarks

The most direct comparison between these two cards is not a clean one, since the database records different test suites for each. The 930A has a single Geekbench OpenCL score of 5317, while the RX 9060 XT has no matching OpenCL entry. Instead, the RX 9060 XT is measured across 3DMark and Passmark tests. Its strongest result is a Passmark G3D score of 20099, which is the headline figure here. That score is roughly 3.8 times the 930A's 5317 OpenCL score, though direct cross-suite comparisons require caution. In pure compute, the RX 9060 XT posts a Passmark GPU Compute score of 11234, which is more than double the 930A's entire OpenCL result.

The 930A, despite its age, does not embarrass itself in the OpenCL test when placed against its nearest recorded rivals. The data shows it sits within 0.8% of four other GPUs: it trails the AMD Radeon R7 M445 by 0.8%, trails the NVIDIA GeForce 840M by 0.1%, and beats the NVIDIA GeForce GTX 980M by 0.2% and the NVIDIA GeForce 940M by 0.6%. Those are essentially ties, which suggests the 930A's OpenCL result is a baseline for low-power mobile GPUs of its generation.

The RX 9060 XT's rival list is a different story. Its average score of 4657 is identical to the AMD Radeon R5 M320, a 0% delta that makes them statistical twins in the database's averaging methodology. However, this average is heavily diluted by legacy DirectX tests. The Passmark DirectX 9 score of 305 and DirectX 11 score of 185 are both low, while the DirectX 10 score is 116 and the DirectX 12 score is just 57. These are not representative of the card's actual capabilities; they are likely artifacts of the test harness or driver path for older APIs. The modern workload score, 3DMark Steel Nomad DX12, is 4093, which is a much more meaningful indicator of current-generation performance.

The biggest single win for the RX 9060 XT is the Passmark G3D score of 20099. This is a modern DirectX 11 aggregate test, and it dwarfs anything the 930A can produce. The 930A's best and only recorded score is 5317, which, even if interpreted as a comparable G3D figure, is less than a third of the RX 9060 XT's G3D result. The RX 9060 XT also wins decisively on GPU compute, with 11234 versus the 930A's 5317, a 2.1x advantage.

There is no recorded head-to-head benchmark between these two cards, and the win tally is 0 for the 930A and 0 for the RX 9060 XT in direct comparison. That absence of direct data means the analysis must rely on the separate benchmark suites and the architecture specs to infer the performance gap.

Where Each One Wins

The 930A wins in one narrow category: legacy OpenCL efficiency relative to its peers. Its score of 5317 is competitive with the GeForce 840M (5322), GTX 980M (5308), 940M (5284), and Radeon R7 M445 (5358). For a 33 W part with 2 GB of DDR3 memory, that result is respectable for its era. This is a card for basic 2D acceleration, light media playback, and very old games at low settings, which is consistent with its 31st percentile ranking and end-of-life production status.

The RX 9060 XT wins in every modern workload category. The Passmark G3D score of 20099 places it in a different performance class entirely. Its Passmark GPU Compute score of 11234 shows strong parallel throughput, backed by 2048 shading units and 25.64 TFLOPS of FP32 compute, which is also matched at 25.64 TFLOPS for FP16 with a 1:1 ratio. The 3DMark Steel Nomad DX12 score of 4093 confirms it can handle modern DirectX 12 titles, a claim the 930A cannot make with its DirectX 12 (11_0) API support.

For users splitting workloads, the RX 9060 XT is the obvious choice for gaming, content creation, and any GPU compute task. The 930A is only viable for systems where power draw is critical (33 W versus 160 W) and where the workload is older, lighter, or non-existent beyond desktop composition. The RX 9060 XT's 16 GB of GDDR6 memory versus 2 GB of DDR3 is another decisive split: modern textures and datasets will not fit in 2 GB. The RX 9060 XT also has 32 ray tracing cores, while the 930A has none, making the newer card the only one with any ray tracing capability.

Architecture Differences

The architectural gap between these two is generational. The 930A uses the GM108 chip on NVIDIA's Maxwell architecture, built on a 28 nm TSMC process. It has 1,020 million transistors on a 77 mm² die, giving a transistor density of 13.2 million per square millimeter. The RX 9060 XT uses the Navi 44 chip on AMD's RDNA 4.0 architecture, built on a 4 nm TSMC process. It packs 29,700 million transistors on a 199 mm² die, which is a density of 149.2 million per square millimeter, more than 11 times the transistor density of the 930A.

The memory subsystem is equally different. The 930A has 2 GB of DDR3 on a 64-bit bus, delivering 16.02 GB/s of bandwidth. The RX 9060 XT has 16 GB of GDDR6 on a 128-bit bus, delivering 322.3 GB/s, which is roughly 20 times the bandwidth. The clock speeds also tell the story: the 930A runs at 928 MHz base and 941 MHz boost, while the RX 9060 XT runs at 1700 MHz base, 2530 MHz game clock, and 3130 MHz boost. The RX 9060 XT's memory runs at 2518 MHz (20.1 Gbps effective), versus the 930A's 1001 MHz (2 Gbps effective).

Compute resources are massively skewed. The 930A has 384 shading units, 24 texture mapping units, and 8 ROPs. The RX 9060 XT has 2048 shading units, 128 TMUs, and 64 ROPs. Pixel rate is 7.528 GPixel/s for the 930A versus 200.3 GPixel/s for the RX 9060 XT. Texture rate is 22.58 GTexel/s versus 400.6 GTexel/s. FP32 throughput is 722.7 GFLOPS versus 25.64 TFLOPS, a 35x difference. The RX 9060 XT also has 32 ray tracing cores, which the 930A entirely lacks.

API support is another differentiator. The 930A supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.4. The RX 9060 XT supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The DirectX 12 Ultimate designation means the RX 9060 XT supports the full feature set of modern DirectX 12, including ray tracing and mesh shaders, while the 930A is limited to a compatibility-level DirectX 12 implementation. Both cards support OpenGL 4.6 and Vulkan 1.4, which is notable for the older card, but the underlying hardware capabilities are not comparable.

The bus interface differs as well: the 930A uses PCIe 3.0 x8, while the RX 9060 XT uses PCIe 5.0 x16. The 930A is an integrated graphics package (IGP) with no power connectors and a 33 W TDP. The RX 9060 XT is a dual-slot card with a single 8-pin power connector and a 160 W TDP, requiring a 450 W power supply. Display outputs on the 930A are portable-device dependent, while the RX 9060 XT offers 1x HDMI 2.1b and 2x DisplayPort 2.1a. The 930A was released on March 12, 2015, and is end-of-life. The RX 9060 XT was released on June 3, 2025, and is active in production. Its launch MSRP is 349 USD.

FAQ

Q: Which card has better raw compute performance?

A: The RX 9060 XT is decisively ahead. It records 25.64 TFLOPS of FP32 compute and a Passmark GPU Compute score of 11234, while the 930A has 722.7 GFLOPS of FP32 and an OpenCL score of 5317.

Q: Can the GeForce 930A handle modern DirectX 12 games?

A: The 930A only supports DirectX 12 (11_0), which is a compatibility feature level, not full DirectX 12 Ultimate. The RX 9060 XT supports DirectX 12 Ultimate (12_2). The 930A's 2 GB of DDR3 memory and 16.02 GB/s bandwidth also limit modern game assets.

Q: How much memory bandwidth does each card have?

A: The 930A has 16.02 GB/s from 2 GB of DDR3 on a 64-bit bus. The RX 9060 XT has 322.3 GB/s from 16 GB of GDDR6 on a 128-bit bus, roughly 20 times more bandwidth.

Q: What is the transistor and process difference?

A: The 930A uses 1,020 million transistors on a 28 nm TSMC process with a 77 mm² die. The RX 9060 XT uses 29,700 million transistors on a 4 nm TSMC process with a 199 mm² die, and a transistor density of 149.2M per mm² versus 13.2M per mm².

Q: Which card supports ray tracing?

A: Only the RX 9060 XT, which has 32 ray tracing cores. The 930A has no ray tracing cores at all.

Q: What are the power requirements?

A: The 930A has a 33 W TDP with no power connectors and is an IGP form factor. The RX 9060 XT has a 160 W TDP, requires a single 8-pin power connector, and needs a 450 W suggested power supply.

The Verdict

The data is unambiguous for any modern workload: the RX 9060 XT is the only viable choice. It has 35 times the FP32 throughput, 20 times the memory bandwidth, 8 times the memory capacity, and the only ray tracing capability. Its Passmark G3D score of 20099 and 3DMark Steel Nomad DX12 score of 4093 place it in a performance tier that the 930A cannot approach. The 930A's 5317 OpenCL score, while competitive with its 2015-era peers, is irrelevant for current software.

The 930A is a historical artifact. It is end-of-life, has 2 GB of memory that cannot hold modern textures, and lacks hardware ray tracing. Its only advantages are the 33 W TDP, which suits fanless or low-power systems, and its compatibility with OpenGL 4.6 and Vulkan 1.4, which is surprising for a Maxwell part but does not compensate for the hardware gap. The RX 9060 XT, with a 160 W TDP and active production status, is the obvious selection for gaming, compute, and content creation. The launch MSRP of 349 USD for the RX 9060 XT places it in the mainstream segment, but no price comparison with the 930A is possible since the 930A has no recorded launch MSRP. For anyone building a system today, the 930A should not be on the list; the RX 9060 XT is the card the data supports.