AMD Radeon RX 590 vs AMD Radeon RX 6700M Comparison

Head-to-Head Benchmarks

The benchmark data available for this comparison is limited to two direct head-to-head tests, but both tell a decisive story. In 3DMark Steel Nomad DX12, the AMD Radeon RX 6700M scores 1845 against the RX 590’s 1081, a 70.7% advantage. This is not a marginal generational step; it is a categorical leap in modern DirectX 12 rasterization throughput. The Radeon RX 6700M’s score places it in the 71st percentile of all GPUs tested, while the RX 590 sits just one point lower at the 70th percentile — a narrow overall ranking gap that belies the magnitude of the direct comparison.

The second head-to-head test, Geekbench Metal, shows an even larger gulf. The RX 6700M posts 91,911, while the RX 590 manages 48,407. That is an 89.9% delta — nearly double the performance. Metal is Apple’s graphics API, and while neither card is primarily designed for macOS workloads, the result confirms that the RX 6700M’s architectural advantages translate across API boundaries, not just within a single benchmark suite.

Looking at average benchmark scores, the RX 6700M aggregates 25,633 across all tested workloads, versus 24,744 for the RX 590. That is a 3.6% aggregate lead, far smaller than the head-to-head deltas suggest. The reason is instructive: the RX 590’s nearest rivals include the NVIDIA RTX A5000 Mobile (24,763, deltaPct -0.1%), the Intel Arc A350M (24,647, deltaPct 0.4%), and the AMD Radeon RX 6600 XT (24,442, deltaPct 1.2%). The RX 6700M’s rivals include the AMD Radeon Pro W5700 (25,726, deltaPct -0.4%) and the NVIDIA GeForce RTX 3080 Ti Mobile (25,740, deltaPct -0.4%). In other words, the RX 590 competes in a lower performance tier, and the RX 6700M competes in a higher one, even though both cards land near the 70th percentile overall.

The wins are unanimous: the RX 6700M takes both head-to-head tests, with a 70.7% win in DX12 and an 89.9% win in Metal. There is no benchmark in the provided data where the RX 590 comes out ahead. This is a clean sweep, and the margin of victory in each test is substantial enough to remove any ambiguity about which GPU is faster in raw compute and rendering tasks.

Architecture Differences

The two cards represent fundamentally different eras of AMD GPU design. The RX 6700M uses the Navi 22 chip on RDNA 2.0 architecture, fabricated on TSMC’s 7 nm process. The RX 590 uses the Polaris 30 chip on GCN 4.0 architecture, fabricated on GlobalFoundries’ 12 nm process. The transistor counts reflect this generational divide: the RX 6700M packs 17,200 million transistors on a 335 mm² die, yielding a transistor density of 51.3 million per square millimeter. The RX 590 has 5,700 million transistors on a 232 mm² die, for a density of 24.6 million per square millimeter. The RX 6700M more than triples the transistor count while using a smaller process node, which explains much of its performance advantage.

Memory configurations differ substantially. The RX 6700M has 10 GB of GDDR6 on a 160-bit bus, delivering 320.0 GB/s of bandwidth with 16 Gbps effective memory speed. The RX 590 has 8 GB of GDDR5 on a 256-bit bus, delivering 256.0 GB/s at 8 Gbps effective. Despite the narrower bus, the RX 6700M achieves 25% more memory bandwidth thanks to the faster GDDR6 standard. The RX 590’s wider bus is a legacy design choice; the RX 6700M’s higher per-pin throughput makes the narrower bus a non-issue.

Compute resources show both similarities and critical differences. Both cards have 2304 shading units and 144 texture mapping units. However, the RX 6700M has 64 render output units (ROPs) versus the RX 590’s 32 — double the pixel throughput capacity. The RX 6700M also introduces 36 ray tracing cores, a feature entirely absent from the RX 590. This is a fundamental architectural addition: RDNA 2.0 includes dedicated hardware for ray-traced workloads, while GCN 4.0 has no such capability.

Clock speeds and derived throughput figures reflect the process and architecture advantages. The RX 6700M has a base clock of 1489 MHz and a boost clock of 2400 MHz, with a game clock of 2300 MHz. The RX 590 has a base clock of 1469 MHz and a boost clock of 1545 MHz. The RX 6700M’s boost clock is 55% higher, and this shows in pixel rate (153.6 GPixel/s vs 49.44 GPixel/s) and texture rate (345.6 GTexel/s vs 222.5 GTexel/s). FP32 compute is 11.06 TFLOPS for the RX 6700M against 7.119 TFLOPS for the RX 590. Notably, the RX 6700M doubles its FP16 throughput to 22.12 TFLOPS via a 2:1 ratio, while the RX 590’s FP16 is 1:1 at 7.119 TFLOPS — a 3.1x advantage in half-precision workloads.

Power and physical specifications differ dramatically. The RX 6700M is rated at 135 W TDP and is an integrated graphics package (IGP) with no power connectors and portable-device-dependent display outputs. The RX 590 is a dual-slot card at 175 W TDP, requiring a 450 W suggested PSU and a single 8-pin power connector, with 1x HDMI 2.0b and 3x DisplayPort 1.4a outputs, and a length of 241 mm (9.5 inches). The RX 6700M also supports PCIe 4.0 x16, while the RX 590 is limited to PCIe 3.0 x16. API support reflects the newer architecture: the RX 6700M supports DirectX 12 Ultimate (12_2) and Vulkan 1.4, while the RX 590 is limited to DirectX 12 (12_0) and Vulkan 1.3.

Where Each One Wins

The RX 6700M wins every benchmark category where data exists. In 3DMark Steel Nomad DX12, it leads by 70.7%. In Geekbench Metal, it leads by 89.9%. Beyond the direct head-to-head, the RX 6700M’s average benchmark score of 25,633 puts it in the 71st percentile, while the RX 590’s 24,744 puts it in the 70th. The RX 6700M’s nearest rivals (AMD Radeon Pro W5700, NVIDIA GeForce RTX 3080 Ti Mobile, AMD FirePro D700, AMD FirePro W7100) all sit within -0.4% to -0.9% of its average score, indicating it is tightly clustered with professional and high-end mobile GPUs. The RX 590’s rivals (NVIDIA RTX A5000 Mobile, Intel Arc A350M, AMD Radeon RX 6600 XT, NVIDIA GeForce GTX 1630) span -0.1% to +1.9%, showing it competes with entry-level and mid-range parts.

The RX 590’s only conceivable wins are in areas not covered by the benchmark data — it has a wider 256-bit memory bus, but that does not translate to a bandwidth advantage (256.0 GB/s vs 320.0 GB/s). It also has a lower TDP at 175 W, but that is a power draw figure, not a performance metric. In every measurable compute or rendering test, the RX 6700M is superior. The RX 590’s 8 GB of GDDR5 memory is smaller and slower than the RX 6700M’s 10 GB of GDDR6, so even in memory-capacity-sensitive workloads, the RX 6700M holds the edge.

For use-case segmentation, the RX 6700M is the clear choice for modern DirectX 12 Ultimate games, ray-traced titles, and compute-heavy workloads that leverage FP16 or Metal API performance. The RX 590, with its GCN 4.0 architecture and DirectX 12 (12_0) support, is suited only for legacy titles or older APIs where its 8 GB frame buffer might suffice, though the data shows no scenario where it outperforms the RX 6700M.

The Verdict

Based strictly on the benchmark data, the AMD Radeon RX 6700M is the superior GPU in every measurable aspect. It wins both head-to-head tests by margins ranging from 70.7% to 89.9%, has a higher average benchmark score (25,633 vs 24,744), and holds a higher percentile ranking (71st vs 70th). The RX 6700M’s architectural advantages — RDNA 2.0 vs GCN 4.0, 7 nm vs 12 nm, 17,200 vs 5,700 million transistors, 36 ray tracing cores vs none, and 320.0 GB/s vs 256.0 GB/s memory bandwidth — fully explain the performance gap.

For users choosing between these two, the data is unambiguous. If the workload involves DirectX 12 or Metal, the RX 6700M is roughly 70-90% faster. If the workload involves ray tracing, only the RX 6700M has the hardware to handle it at all. The RX 590’s only advantages are its lower 175 W TDP (versus 135 W for the RX 6700M, which is actually lower) and its dual-slot form factor with discrete display outputs — but those are physical characteristics, not performance wins. The RX 6700M is the pick for any performance-oriented user. The RX 590 is only defensible if the system requires a dual-slot PCIe 3.0 card with standard display outputs, and even then, the performance deficit is severe.

FAQ

Q: Which GPU has higher raw performance in DirectX 12?

A: The AMD Radeon RX 6700M scores 1845 in 3DMark Steel Nomad DX12, versus 1081 for the RX 590, a 70.7% advantage.

Q: Does the RX 590 have any ray tracing capabilities?

A: No. The RX 590 has no ray tracing cores (rtCores is null), while the RX 6700M has 36 dedicated ray tracing cores.

Q: How do their memory bandwidths compare?

A: The RX 6700M delivers 320.0 GB/s from 10 GB of GDDR6 on a 160-bit bus, while the RX 590 delivers 256.0 GB/s from 8 GB of GDDR5 on a 256-bit bus.

Q: What is the average benchmark score difference?

A: The RX 6700M has an average benchmark score of 25,633, while the RX 590 averages 24,744 — a 3.6% aggregate lead for the RX 6700M.

Q: Which GPU is more power-efficient based on the data?

A: The RX 6700M has a 135 W TDP, while the RX 590 has a 175 W TDP, making the RX 6700M both faster and lower-power.

Q: What API levels do they support?

A: The RX 6700M supports DirectX 12 Ultimate (12_2) and Vulkan 1.4, while the RX 590 supports DirectX 12 (12_0) and Vulkan 1.3.