AMD Radeon R9 M290X vs AMD Radeon RX 6600 XT Comparison

FAQ

Q: How much faster is the RX 6600 XT than the R9 M290X in Geekbench Metal?

A: The RX 6600 XT scores 88,720 in Geekbench Metal, while the R9 M290X scores 24,524. That represents a 261.8% advantage for the RX 6600 XT, meaning it delivers roughly 3.6 times the performance in this compute-oriented API test.

Q: What is the average benchmark score difference between the two cards?

A: The RX 6600 XT has an average benchmark score of 24,442 across all recorded tests, placing it in the 70th percentile of all GPUs. The R9 M290X averages 23,276, sitting in the 68th percentile. Despite a large gap in individual tests, the overall averages are relatively close due to the limited test overlap.

Q: Which card has a higher transistor density, and what does that imply?

A: The RX 6600 XT packs 46.7 million transistors per square millimeter on a 7 nm process, versus 13.2 million per mm² for the R9 M290X on 28 nm. This 3.5x density advantage reflects the much newer manufacturing technology and helps explain the performance disparity.

Q: Does the RX 6600 XT support hardware ray tracing?

A: Yes, the RX 6600 XT includes 32 dedicated ray tracing cores as part of its RDNA 2.0 architecture. The R9 M290X, based on GCN 1.0, has no ray tracing cores at all, making this a fundamental feature difference between the two generations.

Q: What API level does each card support for DirectX?

A: The RX 6600 XT supports DirectX 12 Ultimate (12_2), the highest tier available. The R9 M290X supports DirectX 12 (11_1), which is a lower feature level and lacks some modern rendering capabilities like mesh shaders and variable rate shading.

Q: How do the nearest rivals compare to each card's average score?

A: The RX 6600 XT's closest rival is the Intel Arc A350M, which scores 24,647 — just 0.8% higher. The R9 M290X's nearest rival is the AMD Radeon RX 6600M at 23,273, a virtual tie with 0% difference. Both cards sit in a tight competitive cluster around their respective averages.

Architecture Differences

The architectural gap between these two AMD GPUs spans multiple generations. The RX 6600 XT uses the Navi 23 chip built on RDNA 2.0, manufactured on TSMC's 7 nm process. The R9 M290X uses the Neptune chip based on the much older GCN 1.0 architecture, fabricated on a 28 nm process. This process shrink from 28 nm to 7 nm is the single largest physical difference, enabling the RX 6600 XT to house 11,060 million transistors on a 237 mm² die, while the R9 M290X fits just 2,800 million transistors on a 212 mm² die. The transistor density jumps from 13.2 million per mm² to 46.7 million per mm² — a 3.5x improvement that fundamentally changes what each chip can do per unit area.

The RX 6600 XT features 2,048 shading units, 128 texture mapping units, and 64 raster operation pipelines. It also includes 32 dedicated ray tracing cores, a feature entirely absent from the R9 M290X. The older card offers 1,280 shading units, 80 TMUs, and 32 ROPs. In terms of raw compute throughput, the RX 6600 XT delivers 10.60 TFLOPS of FP32 performance, compared to 2.304 TFLOPS for the R9 M290X — a 4.6x gap. The RX 6600 XT also supports FP16 compute at 21.21 TFLOPS (2:1 rate), while the R9 M290X has no listed FP16 capability.

Memory architecture differs significantly as well. The RX 6600 XT uses 8 GB of GDDR6 on a 128-bit bus, achieving 256.0 GB/s of bandwidth. The R9 M290X uses 4 GB of GDDR5 on a wider 256-bit bus but only reaches 153.6 GB/s due to much slower memory clocks. The newer card's memory runs at 16 Gbps effective, versus 4.8 Gbps effective for the older card. The RX 6600 XT also supports PCIe 4.0 x8, while the R9 M290X is limited to PCIe 3.0 x16.

API support tells a similar story. The RX 6600 XT supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The R9 M290X supports DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.170. The newer card also has a significantly higher boost clock at 2589 MHz versus 900 MHz, with base clocks of 1968 MHz versus 850 MHz. The R9 M290X lists no game clock, while the RX 6600 XT specifies 2359 MHz for gaming workloads.

Head-to-Head Benchmarks

The two cards share only two benchmark results in the data, and the RX 6600 XT wins both decisively. In Geekbench Metal, the RX 6600 XT scores 88,720 against 24,524 for the R9 M290X. This is a 261.8% delta, meaning the newer card is more than 3.6 times faster in Apple's Metal compute API. In Geekbench OpenCL, the margin is even wider: 80,503 versus 22,028, a 265.5% advantage for the RX 6600 XT.

These are not close contests by any measure. The delta percentages are the largest in the entire comparison, and they reflect the fundamental generational leap between GCN 1.0 and RDNA 2.0. The R9 M290X's best result in either test — 24,524 in Metal — is barely above one-quarter of the RX 6600 XT's Metal score. Even the R9 M290X's OpenCL score of 22,028 is less than a third of what the RX 6600 XT achieves in the same test.

The wins tally confirms the dominance: 2 wins for the RX 6600 XT, 0 for the R9 M290X. When placed in context of their nearest rivals, the picture becomes clearer. The RX 6600 XT's average score of 24,442 sits within 1.1% of the NVIDIA GeForce RTX 2080 SUPER (24,170) and just 0.8% behind the GTX 780 Ti (24,236). The R9 M290X's average of 23,276 is effectively tied with the RX 6600M (23,273) and within 0.2% of the AMD Radeon AI PRO R9700 (23,315). Despite the massive head-to-head gap, both cards occupy similar percentile positions overall — 70th for the RX 6600 XT versus 68th for the R9 M290X — because the R9 M290X's limited benchmark data may not fully capture its competitive standing.

Specification Differences

| Specification | AMD Radeon RX 6600 XT | AMD Radeon R9 M290X |

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

| Architecture | RDNA 2.0 | GCN 1.0 |

| Process Node | 7 nm | 28 nm |

| Transistors | 11,060 million | 2,800 million |

| Die Size | 237 mm² | 212 mm² |

| Transistor Density | 46.7M / mm² | 13.2M / mm² |

| Base Clock | 1968 MHz | 850 MHz |

| Boost Clock | 2589 MHz | 900 MHz |

| Game Clock | 2359 MHz | — |

| Memory Size | 8 GB | 4 GB |

| Memory Type | GDDR6 | GDDR5 |

| Memory Bus | 128 bit | 256 bit |

| Memory Bandwidth | 256.0 GB/s | 153.6 GB/s |

| Memory Clock | 16 Gbps effective | 4.8 Gbps effective |

| Shading Units | 2048 | 1280 |

| TMUs | 128 | 80 |

| ROPs | 64 | 32 |

| Ray Tracing Cores | 32 | — |

| Pixel Rate | 165.7 GPixel/s | 28.80 GPixel/s |

| Texture Rate | 331.4 GTexel/s | 72.00 GTexel/s |

| FP32 Performance | 10.60 TFLOPS | 2.304 TFLOPS |

| FP16 Performance | 21.21 TFLOPS (2:1) | — |

| TDP | 160 W | 100 W |

| Slot Width | Dual-slot | MXM Module |

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

| Bus Interface | PCIe 4.0 x8 | PCIe 3.0 x16 |

| Display Outputs | 1x HDMI 2.1, 3x DisplayPort 1.4a | Portable Device Dependent |

| DirectX Support | 12 Ultimate (12_2) | 12 (11_1) |

| Vulkan Support | 1.4 | 1.2.170 |

| Release Date | 2021-07-29 | 2014-01-08 |

| Launch MSRP | 379 USD | — |

Where Each One Wins

The RX 6600 XT wins everywhere the data measures. In both shared benchmarks — Geekbench Metal and Geekbench OpenCL — it dominates with margins exceeding 260%. Beyond raw scores, the RX 6600 XT holds advantages in every meaningful specification category: higher clocks, more memory, faster memory, more shading units, more TMUs, more ROPs, and the only ray tracing hardware. Its 8 GB frame buffer is double the R9 M290X's 4 GB, which matters for modern games with large texture sets. The newer card also supports DirectX 12 Ultimate and Vulkan 1.4, giving it access to features like mesh shaders and variable rate shading that the older card cannot use.

The R9 M290X does have a few theoretical advantages, though they are narrow. Its 256-bit memory bus is twice as wide as the RX 6600 XT's 128-bit bus, and its 100 W TDP is significantly lower than 160 W. It also uses an MXM module form factor with no power connectors, making it suitable for laptop implementations, whereas the RX 6600 XT is a dual-slot desktop card requiring a 1x 8-pin connector and a 450 W recommended PSU. For mobile applications, the R9 M290X's lower power draw and compact form factor could be preferable, though the RX 6600 XT's performance advantage would be difficult to sacrifice in most scenarios.

In terms of competitive positioning, the RX 6600 XT's nearest rivals include the NVIDIA GeForce GTX 1630 (0.7% lower average score), the Intel Arc A350M (0.8% higher), and the GTX 780 Ti (0.8% lower). The R9 M290X sits in a cluster with the RX 6600M (0% delta), Pro Vega 16 (0.1% higher), P106-100 (0.1% higher), and AI PRO R9700 (0.2% lower). Neither card is an outlier in its respective performance tier; both are competitive within their generations.

The Verdict

The data makes the choice unambiguous for almost any use case. The RX 6600 XT is the superior card by every metric that appears in the benchmark results and specification comparisons. Its 261.8% Metal advantage and 265.5% OpenCL advantage over the R9 M290X are overwhelming, and its 70th percentile standing versus 68th percentile overall placement confirms that the newer card is the stronger performer in absolute terms.

The RX 6600 XT is the clear pick for desktop gaming, content creation, or any workload that can leverage DirectX 12 Ultimate features, ray tracing, or high FP32 throughput. Its 8 GB GDDR6 memory and 256.0 GB/s bandwidth provide ample headroom for modern titles, and its 10.60 TFLOPS FP32 performance is more than four times what the R9 M290X can muster. The 379 USD launch MSRP positions it as a mainstream option, though pricing considerations are outside this analysis.

The R9 M290X retains relevance only in very specific scenarios. Its 100 W TDP, MXM Module form factor, and lack of power connectors make it suitable for older laptop systems where the RX 6600 XT physically cannot fit. For users constrained to that form factor, the R9 M290X offers 2.304 TFLOPS of FP32 performance and 4 GB of GDDR5 memory on a 256-bit bus, which is respectable for its era but severely outdated by modern standards. Its DirectX 12 (11_1) support and Vulkan 1.2.170 compatibility limit its ability to run the newest titles with advanced rendering features.

For anyone choosing between these two cards for a new build or upgrade, the RX 6600 XT wins without qualification. The gap in architecture, compute, memory, and features is simply too large for the R9 M290X to overcome. Users with legacy MXM-based systems should consider whether their platform can accommodate a different card entirely, as the R9 M290X's performance ceiling will likely struggle with modern workloads. The verdict from the data is clear: the RX 6600 XT is the only rational choice unless the R9 M290X's specific form factor is an absolute requirement.