AMD Radeon RX 590 vs NVIDIA RTX A5000 Mobile Comparison

The NVIDIA RTX A5000 Mobile and AMD Radeon RX 590 occupy nearly the same performance tier according to aggregate data, with the A5000 Mobile posting an average benchmark score of 24,763 against the RX 590’s 24,744, a razor-thin 0.1% delta. Yet these two GPUs come from fundamentally different worlds: one is a mobile workstation-class chip built on a 8nm process with 16GB of GDDR6, while the other is a desktop gaming card from an older 12nm node with 8GB of GDDR5. The data suggests that while their overall averages align, their architectural priorities and intended workloads diverge sharply, making the choice between them less about raw score and more about what specific tasks matter most.

Where Each One Wins

The RTX A5000 Mobile is the clear winner in modern compute-heavy workloads. Its Geekbench OpenCL score of 110,877 dwarfs the RX 590’s available benchmark results, which include only a 3DMark Steel Nomad DX12 score of 1,081 and a Geekbench Metal score of 48,407. The A5000 Mobile also excels in PassMark’s compute test, scoring 6,945, a figure that reflects its 6,144 shading units and 192 tensor cores. For users running machine learning inference, ray-traced rendering, or any task that leverages DirectX 12 Ultimate features, the A5000 Mobile’s architecture provides capabilities the RX 590 simply lacks, as the RX 590 has no RT cores or tensor cores at all.

The RX 590, meanwhile, wins in the legacy DirectX 9 and DirectX 11 categories, where it posts PassMark scores of 169 and 133, respectively, versus the A5000 Mobile’s 169 and 115 in those same tests. The RX 590 also has a higher PassMark DirectX 10 score of 115 compared to the A5000 Mobile’s 115, though that is a tie. More telling is the RX 590’s PassMark G2D score of 629 against the A5000 Mobile’s 629 — another exact tie. The RX 590’s advantage in older APIs points to its design as a straightforward rasterization card, optimized for the game libraries of its era rather than future-proofing features.

The A5000 Mobile’s PassMark G3D score of 15,779 versus the RX 590’s lack of that specific benchmark further complicates direct comparison, but the aggregate numbers show both GPUs landing at the 70th percentile among all GPUs. In practice, the A5000 Mobile is the pick for professional, compute-heavy, and forward-looking workloads, while the RX 590 remains competitive for older DirectX titles and basic 2D tasks, where its scores match or exceed the newer mobile chip.

Architecture Differences

The two GPUs are built on entirely different architectural philosophies. The RTX A5000 Mobile uses NVIDIA’s Ampere architecture on a GA104 chip, fabricated by Samsung on an 8nm process. It packs 17,400 million transistors into a 392 mm² die, achieving a transistor density of 44.4 million per square millimeter. This is a massive, feature-rich chip designed to handle parallel compute, with 48 RT cores for ray tracing and 192 tensor cores for AI acceleration. Its 6,144 shading units, 192 texture mapping units, and 96 render output units give it a pixel rate of 151.2 GPixel/s and a texture rate of 302.4 GTexel/s, alongside a FP32 throughput of 19.35 TFLOPS.

The RX 590, in contrast, uses AMD’s older GCN 4.0 architecture on the Polaris 30 chip, made by GlobalFoundries on a 12nm process. It contains 5,700 million transistors on a 232 mm² die, with a density of 24.6 million per square millimeter. This is a leaner, simpler design with 2,304 shading units, 144 TMUs, and just 32 ROPs. Its pixel rate is 49.44 GPixel/s and texture rate is 222.5 GTexel/s, with FP32 performance of 7.119 TFLOPS. Notably, the RX 590 has no RT cores or tensor cores, reflecting its focus on traditional rasterization. The A5000 Mobile’s FP16 performance matches its FP32 at 19.35 TFLOPS, indicating a 1:1 ratio, while the RX 590 also runs FP16 at 7.119 TFLOPS, again 1:1 — the raw throughput difference is stark.

The memory subsystems also diverge: the A5000 Mobile uses 16GB of GDDR6 on a 256-bit bus, yielding 448.0 GB/s of bandwidth, while the RX 590 uses 8GB of GDDR5 on a 256-bit bus, capped at 256.0 GB/s. The A5000 Mobile’s memory clock is 1750 MHz (14 Gbps effective), versus the RX 590’s 2000 MHz (8 Gbps effective) — the latter’s higher clock is offset by the older memory type’s lower effective rate. These differences mean the A5000 Mobile can feed its far larger shader array and AI accelerators, while the RX 590’s bandwidth is tailored to its more modest compute demands.

Head-to-Head Benchmarks

Direct head-to-head benchmark data is sparse, as the FACT PACK lists no shared test results between the two GPUs. However, the available individual scores allow for meaningful comparisons across different metrics. The RTX A5000 Mobile’s Geekbench OpenCL score of 110,877 is its standout result, indicating exceptional general-purpose compute performance. The RX 590 does not have an OpenCL score listed, but its Geekbench Metal score of 48,407 is less than half of the A5000 Mobile’s OpenCL number, suggesting a significant gap in raw compute throughput when accounting for the different APIs.

In PassMark tests, the A5000 Mobile leads in DirectX 11 with 133 versus the RX 590’s 115, a 15.7% advantage. It also leads in DirectX 12 with 72 versus the RX 590’s 72 — an exact tie — and in GPU compute with 6,945 versus the RX 590’s lack of that score. The RX 590 matches or edges ahead in older APIs: it ties the A5000 Mobile at 169 in DirectX 9, ties at 115 in DirectX 10, and ties at 629 in G2D. The RX 590’s 3DMark Steel Nomad DX12 score of 1,081 is its only modern benchmark, and the A5000 Mobile has no comparable 3DMark result, so that score stands alone.

The aggregate picture is one of near-total parity: the A5000 Mobile’s average score of 24,763 is only 0.1% ahead of the RX 590’s 24,744. This tiny delta masks the fact that the two GPUs excel in different domains — the A5000 Mobile dominates in compute and newer APIs, while the RX 590 holds its own in legacy DirectX and 2D performance. For a user running only DirectX 9 games, the RX 590 would be indistinguishable from the A5000 Mobile; for a user running OpenCL workloads, the A5000 Mobile is in a different league.

Specification Differences

The most glaring specification gap is in memory: the A5000 Mobile offers 16GB of GDDR6 with 448.0 GB/s bandwidth, while the RX 590 has 8GB of GDDR5 with 256.0 GB/s bandwidth. The A5000 Mobile’s shading units number 6,144 versus 2,304 for the RX 590, and its TMUs are 192 versus 144. ROPs differ even more sharply: 96 for the A5000 Mobile versus 32 for the RX 590. The A5000 Mobile features 48 RT cores and 192 tensor cores, which the RX 590 entirely lacks. Clock speeds also differ: the A5000 Mobile runs at a 900 MHz base and 1575 MHz boost, while the RX 590 runs at 1469 MHz base and 1545 MHz boost — the RX 590’s higher base clock is a legacy of its simpler design, but its boost clock is actually lower.

The process node separates them further: 8nm Samsung for the A5000 Mobile versus 12nm GlobalFoundries for the RX 590. Transistor counts are 17,400 million versus 5,700 million, and die sizes are 392 mm² versus 232 mm². Power consumption shows the A5000 Mobile at 150W TDP with no power connectors (as a mobile chip), while the RX 590 draws 175W and requires a 1x 8-pin connector with a suggested 450W PSU. The RX 590 is a dual-slot card at 241mm in length, whereas the A5000 Mobile has no listed dimensions due to its portable-device-dependent nature. The bus interface differs: PCIe 4.0 x16 for the A5000 Mobile versus PCIe 3.0 x16 for the RX 590. API support also diverges, with the A5000 Mobile supporting DirectX 12 Ultimate (12_2) and Vulkan 1.4, while the RX 590 maxes out at DirectX 12 (12_0) and Vulkan 1.3. The RX 590 has a launch MSRP of 279 USD, which is noted for reference only.

FAQ

Q: Which GPU has higher raw compute performance?

A: The RTX A5000 Mobile is far ahead, with 19.35 TFLOPS FP32 versus the RX 590’s 7.119 TFLOPS, and its Geekbench OpenCL score of 110,877 dwarfs the RX 590’s Geekbench Metal score of 48,407.

Q: Do both GPUs support ray tracing?

A: No. The RTX A5000 Mobile has 48 dedicated RT cores, while the RX 590 has no RT cores at all, meaning it cannot perform hardware-accelerated ray tracing.

Q: How do they compare in memory capacity and bandwidth?

A: The A5000 Mobile has 16GB of GDDR6 with 448.0 GB/s bandwidth, while the RX 590 has 8GB of GDDR5 with 256.0 GB/s bandwidth, giving the A5000 Mobile double the capacity and roughly 75% more bandwidth.

Q: Which GPU is better for older DirectX games?

A: The RX 590 matches or slightly exceeds the A5000 Mobile in PassMark DirectX 9 (169 vs 169), DirectX 10 (115 vs 115), and DirectX 11 (133 vs 115), making it equally capable or better for legacy titles.

Q: What is the performance gap in overall average scores?

A: The A5000 Mobile’s average score is 24,763 versus the RX 590’s 24,744, a delta of just 0.1%, placing both GPUs at the 70th percentile among all GPUs.

Q: Are there any benchmarks where the RX 590 wins outright?

A: The RX 590 wins in PassMark DirectX 11 with 133 versus 115 for the A5000 Mobile, and it also posts a 3DMark Steel Nomad DX12 score of 1,081, though the A5000 Mobile has no comparable 3DMark result.

The Verdict

The data points to a clear split based on workload. The RTX A5000 Mobile is the superior choice for anyone prioritizing compute performance, modern API support, ray tracing, or AI acceleration — its 6,144 shading units, 192 tensor cores, and 19.35 TFLOPS FP32 throughput leave the RX 590 far behind in any task that leverages those resources. Its 16GB of memory and 448.0 GB/s bandwidth also make it better suited for large datasets or high-resolution textures. The RX 590, however, is not obsolete: it matches or beats the A5000 Mobile in legacy DirectX 9 and 10 tests, ties in DirectX 12 and G2D performance, and does so at a lower 175W TDP with a simpler dual-slot design that fits traditional desktop builds.

For a professional user running OpenCL compute or modern DirectX 12 Ultimate workloads, the A5000 Mobile is the obvious pick. For a gamer stuck on older DirectX 11 titles or needing a cheap, straightforward desktop card, the RX 590 holds its ground. The 0.1% aggregate score difference is misleading — it hides the fact that these are specialized tools for different jobs. The A5000 Mobile is a forward-looking compute powerhouse; the RX 590 is a reliable legacy rasterizer. Choose based on the benchmarks that match your actual use case, not the overall average.