AMD Radeon RX 590 GME vs AMD Radeon RX 6800M Comparison

Head-to-Head Benchmarks

The recorded data shows a decisive overall victory for the AMD Radeon RX 6800M across every shared benchmark test. Out of three head-to-head comparisons, the RX 6800M wins all three, while the RX 590 GME does not secure a single win. The margin of victory varies significantly by workload, with the largest gap appearing in compute-oriented tests.

In the 3DMark Steel Nomad DX12 test, the RX 6800M scores 2,238 points against the RX 590 GME's 1,001 points. That is a delta of 55.3% in favor of the RX 6800M. This is a substantial lead in a modern DirectX 12 gaming workload, indicating that the newer architecture handles contemporary rendering paths with considerably more efficiency.

The Geekbench OpenCL test shows an even larger divide. The RX 6800M posts 87,621 points, while the RX 590 GME manages 36,294 points. The delta here is 58.6%, meaning the RX 6800M is more than double the score of the older card. OpenCL is a general-purpose compute benchmark, and this result highlights the raw throughput advantage of the RDNA 2.0 design, particularly in parallel processing tasks.

The Vulkan API test narrows the gap somewhat but still favors the RX 6800M. The RX 6800M scores 94,766 points, while the RX 590 GME reaches 60,508 points. The delta is 36.2%, the smallest of the three comparisons. Vulkan's lower overhead can benefit older architectures, which likely explains why the RX 590 GME performs relatively better here than in OpenCL or DX12. Still, the RX 6800M maintains a commanding lead.

Looking at the average benchmark scores across all recorded tests, the RX 590 GME averages 32,601 points, while the RX 6800M averages 28,874 points. This is an interesting inversion: despite losing every head-to-head test, the RX 590 GME has a higher average score across its full benchmark suite. The reason is that the RX 6800M's average includes several low-scoring PassMark tests (DirectX 10, 11, 12, 9, 2D, 3D, and compute), which drag down its mean. The RX 590 GME's benchmark set is smaller and contains only higher-scoring tests. Thus, the average benchmark score should not be interpreted as a measure of relative performance; the head-to-head tests are the more reliable indicator.

The percentile rankings also tell a nuanced story. The RX 590 GME sits at the 77th percentile among all GPUs, while the RX 6800M sits at the 74th percentile. Despite the RX 6800M's dominance in direct comparisons, its percentile is slightly lower, again reflecting the mixed benchmark suite on the mobile part. The RX 590 GME's nearest rivals in the database include the AMD FirePro S9300 X2 (0.2% ahead), the AMD Radeon RX 7900 GRE (0.4% ahead), and the AMD FirePro S10000 (0.7% ahead), with the NVIDIA T600 Mobile 0.8% behind. The RX 6800M's nearest rivals are the AMD Radeon RX 570 (0.4% ahead), the AMD Radeon R9 M295X (1% ahead), and the Intel Arc A370M (1% behind), with the AMD Radeon RX 470 0.4% ahead. This places the RX 6800M in a peer group of mid-range and older desktop cards, which is notable for a mobile GPU.

Where Each One Wins

The RX 6800M wins in every shared test category, but the degree of its advantage varies by workload type. In modern DirectX 12 gaming, it is 55.3% ahead. This is the kind of workload that benefits most from the architectural improvements in RDNA 2.0, including hardware ray tracing support and a more efficient shader pipeline. The RX 590 GME's GCN 4.0 architecture, while still functional in DX12 titles, clearly cannot match the throughput of the newer design.

In compute-heavy OpenCL workloads, the RX 6800M is 58.6% ahead. This is its largest margin, reflecting the higher FP32 throughput (12.24 TFLOPS versus 6.543 TFLOPS) and the greater number of shading units (2,560 versus 2,304). The RX 6800M also has double the pixel rate (153.0 GPixel/s versus 45.44 GPixel/s) and a significantly higher texture rate (382.4 GTexel/s versus 204.5 GTexel/s), which helps in both compute and rasterization tasks.

In Vulkan workloads, the RX 6800M is 36.2% ahead. This is the closest result, suggesting that the RX 590 GME's older architecture handles Vulkan's explicit control model reasonably well. Still, the RX 6800M's raw hardware advantages, including 64 ROPs versus 32, and a higher memory bandwidth (384.0 GB/s versus 256.0 GB/s), keep it firmly ahead.

There is no benchmark category in which the RX 590 GME wins. Its only statistical advantage is the higher average benchmark score (32,601 versus 28,874) and the higher percentile ranking (77th versus 74th), but these are artifacts of the different test suites rather than genuine performance strengths. The RX 6800M's PassMark scores, which include low values like 101 in DirectX 10, 127 in DirectX 11, and 65 in DirectX 12, are likely measured under different conditions or with a different methodology, so they should not be compared directly to the RX 590 GME's scores.

For users prioritizing modern gaming with ray tracing, the RX 6800M is the clear choice. For users running older API workloads or Vulkan-based titles, the RX 6800M still leads, though by a smaller margin. The RX 590 GME remains a viable option only in scenarios where its lower power draw or desktop form factor matters, but its performance ceiling is noticeably lower.

Architecture Differences

The two GPUs come from different architectural generations and manufacturing processes. The RX 590 GME uses the Polaris 20 chip built on GCN 4.0 architecture, fabricated on a 14 nm process at GlobalFoundries. It contains 5,700 million transistors on a 232 mm² die, giving a transistor density of 24.6 million per square millimeter. The RX 6800M uses the Navi 22 chip built on RDNA 2.0 architecture, fabricated on a 7 nm process at TSMC. It contains 17,200 million transistors on a 335 mm² die, giving a transistor density of 51.3 million per square millimeter. The shift from 14 nm to 7 nm allows the RX 6800M to pack nearly three times as many transistors into a die that is only 44% larger.

The core configurations differ in several key ways. The RX 590 GME has 2,304 shading units, 144 texture mapping units, and 32 ROPs. The RX 6800M has 2,560 shading units, 160 TMUs, and 64 ROPs. The RX 6800M also includes 40 ray tracing cores, a feature entirely absent from the RX 590 GME. This is the first major architectural addition that enables hardware-accelerated ray tracing in DirectX 12 Ultimate titles. The RX 590 GME supports DirectX 12 (12_0), while the RX 6800M supports DirectX 12 Ultimate (12_2), which includes features like variable rate shading and mesh shaders in addition to ray tracing.

Clock speeds are substantially higher on the RX 6800M. Its base clock is 2,116 MHz, with a boost clock of 2,390 MHz and a game clock of 2,300 MHz. The RX 590 GME has a base clock of 1,257 MHz and a boost clock of 1,420 MHz, with no game clock listed. The RX 6800M's higher clocks, combined with its larger shader count, produce an FP32 throughput of 12.24 TFLOPS, nearly double the RX 590 GME's 6.543 TFLOPS. In FP16, the RX 6800M achieves 24.47 TFLOPS (2:1 ratio), while the RX 590 GME is capped at 6.543 TFLOPS (1:1 ratio), meaning it offers no FP16 acceleration advantage.

Memory subsystems also diverge. The RX 590 GME uses 8 GB of GDDR5 on a 256-bit bus, delivering 256.0 GB/s of bandwidth at 2000 MHz (8 Gbps effective). The RX 6800M uses 12 GB of GDDR6 on a 192-bit bus, delivering 384.0 GB/s of bandwidth at 2000 MHz (16 Gbps effective). Despite the narrower bus, the faster GDDR6 memory gives the RX 6800M a 50% bandwidth advantage. The RX 6800M also benefits from PCIe 4.0 x16 connectivity, while the RX 590 GME is limited to PCIe 3.0 x16. The RX 6800M supports Vulkan 1.4, while the RX 590 GME supports Vulkan 1.3. Both support OpenGL 4.6.

Power and physical characteristics differ as well. The RX 590 GME has a TDP of 175 W, requires a single 8-pin power connector, and is a dual-slot card measuring 241 mm (9.5 inches) in length. The RX 6800M has a TDP of 145 W, uses no power connectors (it is an integrated GPU for laptops, classified as IGP slot width), and has no listed dimensions. The RX 590 GME's suggested PSU is 450 W, while the RX 6800M has no suggested PSU listed. The RX 590 GME offers display outputs of 1x HDMI 2.0b and 3x DisplayPort 1.4a, while the RX 6800M's outputs are portable device dependent.

FAQ

Q: Which GPU wins the most benchmark comparisons?

A: The AMD Radeon RX 6800M wins all three head-to-head tests against the RX 590 GME, with deltas of 55.3% in 3DMark Steel Nomad DX12, 58.6% in Geekbench OpenCL, and 36.2% in Geekbench Vulkan.

Q: Why does the RX 590 GME have a higher average benchmark score than the RX 6800M?

A: The RX 590 GME averages 32,601 points versus 28,874 for the RX 6800M, but this is due to the RX 6800M's larger test suite including low-scoring PassMark scores, not due to superior performance in shared tests. In all shared tests, the RX 6800M leads by double-digit percentages.

Q: Does the RX 6800M support ray tracing?

A: Yes, the RX 6800M includes 40 ray tracing cores and supports DirectX 12 Ultimate (12_2). The RX 590 GME has no ray tracing cores and supports only DirectX 12 (12_0).

Q: What are the memory specifications of each GPU?

A: The RX 590 GME has 8 GB of GDDR5 on a 256-bit bus with 256.0 GB/s bandwidth. The RX 6800M has 12 GB of GDDR6 on a 192-bit bus with 384.0 GB/s bandwidth.

Q: Which GPU has the higher boost clock?

A: The RX 6800M has a boost clock of 2,390 MHz, while the RX 590 GME has a boost clock of 1,420 MHz. The RX 6800M also has a higher base clock (2,116 MHz versus 1,257 MHz).

Q: What is the process node difference between the two GPUs?

A: The RX 590 GME is built on a 14 nm process at GlobalFoundries, while the RX 6800M is built on a 7 nm process at TSMC. The RX 6800M also has a higher transistor density at 51.3M per square millimeter versus 24.6M per square millimeter.

Specification Differences

| Specification | AMD Radeon RX 590 GME | AMD Radeon RX 6800M |

|---|---|---|

| Architecture | GCN 4.0 | RDNA 2.0 |

| Process Node | 14 nm | 7 nm |

| Foundry | GlobalFoundries | TSMC |

| Transistors | 5,700 million | 17,200 million |

| Die Size | 232 mm² | 335 mm² |

| Transistor Density | 24.6M / mm² | 51.3M / mm² |

| Base Clock | 1257 MHz | 2116 MHz |

| Boost Clock | 1420 MHz | 2390 MHz |

| Game Clock | None | 2300 MHz |

| Memory Size | 8 GB | 12 GB |

| Memory Type | GDDR5 | GDDR6 |

| Memory Bus Width | 256 bit | 192 bit |

| Memory Bandwidth | 256.0 GB/s | 384.0 GB/s |

| Memory Effective Speed | 8 Gbps | 16 Gbps |

| Shading Units | 2304 | 2560 |

| TMUs | 144 | 160 |

| ROPs | 32 | 64 |

| Ray Tracing Cores | None | 40 |

| Pixel Rate | 45.44 GPixel/s | 153.0 GPixel/s |

| Texture Rate | 204.5 GTexel/s | 382.4 GTexel/s |

| FP32 | 6.543 TFLOPS | 12.24 TFLOPS |

| FP16 | 6.543 TFLOPS (1:1) | 24.47 TFLOPS (2:1) |

| TDP | 175 W | 145 W |

| Slot Width | Dual-slot | IGP |

| Power Connectors | 1x 8-pin | None |

| Suggested PSU | 450 W | None |

| Bus Interface | PCIe 3.0 x16 | PCIe 4.0 x16 |

| Display Outputs | 1x HDMI 2.0b, 3x DisplayPort 1.4a | Portable Device Dependent |

| DirectX Support | 12 (12_0) | 12 Ultimate (12_2) |

| Vulkan Support | 1.3 | 1.4 |

| Release Date | 2020-03-08 | 2021-05-30 |

| Predecessor | Arctic Islands | Polaris Mobile |

| Successor | Vega | None |

| Production Status | End-of-life | End-of-life |