AMD Radeon R9 M290X vs AMD Radeon RX 6750 XT Comparison

The Verdict

The AMD Radeon RX 6750 XT and the AMD Radeon R9 M290X occupy entirely different tiers of the performance spectrum, separated by eight years of architectural progress. The RX 6750 XT is the clear choice for any desktop build requiring modern API support, high-resolution rendering, and substantial compute throughput. Its average benchmark score of 26011 places it 71st percentile among all GPUs, while the R9 M290X sits at 68th percentile with an average score of 23276. For users seeking raw performance in current DirectX 12 Ultimate titles, the RX 6750 XT dominates. For those constrained to legacy mobile platforms where the R9 M290X's MXM form factor and 100 W power envelope are the only options, it remains a functional, if dated, solution.

The R9 M290X wins only one recorded head-to-head test, Geekbench OpenCL, where it posts 22028 against the RX 6750 XT's 16360, a delta of 25.7% in its favor. This is a narrow, workload-specific victory. The RX 6750 XT counters in Geekbench Metal with a score of 137249 versus 24524, a 459.7% advantage. The data suggests that the RX 6750 XT is the only sensible pick for new purchases, while the R9 M290X should be considered solely for replacement purposes in legacy systems where its MXM module interface is required.

Architecture Differences

The two GPUs come from different architectural families and different process technologies. The RX 6750 XT uses the Navi 22 chip on RDNA 2.0 architecture, built on TSMC's 7 nm process. It integrates 17,200 million transistors on a 335 mm² die, yielding a transistor density of 51.3M per mm². The R9 M290X uses the Neptune chip on GCN 1.0 architecture, fabricated on TSMC's 28 nm process. It packs 2,800 million transistors into a 212 mm² die, with a transistor density of 13.2M per mm². The RX 6750 XT's density advantage reflects the newer process node and the compactness of RDNA 2.0's design.

The RX 6750 XT belongs to the Navi II (RX 6000) generation, with Navi as its predecessor and Navi III as its successor. The R9 M290X is part of the Gem System (R9 M200) generation, preceded by Solar System and succeeded by Polaris Mobile. The RX 6750 XT carries 2560 shading units, 160 texture mapping units, 64 render output units, and 40 ray tracing cores. The R9 M290X has 1280 shading units, 80 TMUs, and 32 ROPs, with no ray tracing cores. The RX 6750 XT's shading unit count is exactly double that of the R9 M290X, and its TMU and ROP counts are likewise doubled.

Memory architecture also diverges sharply. The RX 6750 XT has 12 GB of GDDR6 on a 192-bit bus, delivering 432.0 GB/s of bandwidth. The R9 M290X has 4 GB of GDDR5 on a 256-bit bus, providing 153.6 GB/s. Although the R9 M290X has a wider bus, the GDDR6 standard and higher clock speeds on the RX 6750 XT produce nearly three times the bandwidth. The RX 6750 XT supports PCIe 4.0 x16, while the R9 M290X uses PCIe 3.0 x16.

API support differs meaningfully. The RX 6750 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 RX 6750 XT's ray tracing hardware and modern feature set make it compliant with the latest 12_2 specification, while the R9 M290X's older shader model and lack of RT cores limit it to the 11_1 subset. The R9 M290X also lacks FP16 capabilities entirely; the RX 6750 XT provides 26.62 TFLOPS FP16 with a 2:1 ratio, whereas the R9 M290X lists no FP16 figure at all.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon RX 6750 XT has an average benchmark score of 26011, while the AMD Radeon R9 M290X scores 23276. The RX 6750 XT sits at 71st percentile among all GPUs, the R9 M290X at 68th.

Q: How does the RX 6750 XT compare to its nearest rivals?

A: The RX 6750 XT's closest rival is the AMD Radeon R9 M395X, which averages 25891 with a 0.5% delta, and the AMD FirePro W7100 at 25856 with a 0.6% delta. The NVIDIA GeForce RTX 3080 Ti Mobile trails at 25740 with a 1.1% delta. The RX 6750 XT leads all four listed rivals in average score.

Q: What are the R9 M290X's nearest competitors?

A: The AMD Radeon RX 6600M is essentially tied at 23273 with a 0% delta, followed by the AMD Radeon Pro Vega 16 at 23250 with a 0.1% delta, the NVIDIA P106-100 at 23249 with a 0.1% delta, and the AMD Radeon AI PRO R9700 at 23315 with a 0.2% delta in the R9 M290X's favor.

Q: Which GPU wins in Geekbench Metal?

A: The RX 6750 XT wins decisively with a score of 137249 against the R9 M290X's 24524, a 459.7% advantage in the RX 6750 XT's favor.

Q: Which GPU wins in Geekbench OpenCL?

A: The AMD Radeon R9 M290X wins with 22028 against the RX 6750 XT's 16360, a 25.7% margin for the R9 M290X.

Q: What is the memory bandwidth difference?

A: The RX 6750 XT delivers 432.0 GB/s from 12 GB of GDDR6 on a 192-bit bus. The R9 M290X provides 153.6 GB/s from 4 GB of GDDR5 on a 256-bit bus. The RX 6750 XT offers approximately 2.8 times the bandwidth.

Specification Differences

The two cards differ across nearly every specification field. The RX 6750 XT uses a 7 nm process, while the R9 M290X uses 28 nm. Transistor counts are 17,200 million versus 2,800 million, a six-fold difference. Die size is 335 mm² versus 212 mm². Transistor density is 51.3M per mm² versus 13.2M per mm².

Clock speeds: the RX 6750 XT has a base clock of 2150 MHz and a boost clock of 2600 MHz, with a game clock of 2495 MHz. The R9 M290X has a base clock of 850 MHz and a boost clock of 900 MHz, with no game clock listed. Memory clock is 2250 MHz (18 Gbps effective) on the RX 6750 XT, versus 1200 MHz (4.8 Gbps effective) on the R9 M290X.

Memory configurations: 12 GB GDDR6 on a 192-bit bus with 432.0 GB/s bandwidth for the RX 6750 XT; 4 GB GDDR5 on a 256-bit bus with 153.6 GB/s for the R9 M290X. The RX 6750 XT has 2560 shading units, 160 TMUs, 64 ROPs, and 40 RT cores. The R9 M290X has 1280 shading units, 80 TMUs, 32 ROPs, and no RT cores.

Pixel and texture rates: the RX 6750 XT achieves 166.4 GPixel/s and 416.0 GTexel/s. The R9 M290X achieves 28.80 GPixel/s and 72.00 GTexel/s. FP32 compute is 13.31 TFLOPS versus 2.304 TFLOPS. FP16 compute is 26.26 TFLOPS (2:1) on the RX 6750 XT, with no figure listed for the R9 M290X.

Power and physical specs: the RX 6750 XT has a TDP of 250 W, is dual-slot, uses 1x 6-pin plus 1x 8-pin power connectors, and recommends a 600 W PSU. The R9 M290X has a TDP of 100 W, is an MXM module with no power connectors, and no PSU recommendation. Bus interface is PCIe 4.0 x16 for the RX 6750 XT and PCIe 3.0 x16 for the R9 M290X.

Display outputs: the RX 1.0 XT provides 1x HDMI 2.1 and 3x DisplayPort 1.4a. The R9 M290X outputs are listed as Portable Device Dependent. The RX 6750 XT has dimensions of 267 mm length, 110 mm height, 40 mm width. The R9 M290X lists no dimensions at all.

The RX 6750 XT has a launch MSRP of 549 USD; the R9 M290X has no launch MSRP is not listed. The RX 6750 XT is end-of-life, as is the R9 M290X. Release date for the RX 6750 XT is 2022-03-02; the R9 M290X date is 2014-01-08.

Head-to-Head Benchmarks

The head-to-head data consists of two Geekbench tests with opposite outcomes. The first, Geekbench Metal, is a landslide for the RX 6750 XT. Its score of 137249 dwarfs the R9 M290X's 24524, a 459.7% delta. This is the single largest performance gap in the recorded data. The Metal test exercises the GPU's modern feature set and memory bandwidth, both of which favor the RX 6750 XT. The 432.0 GB/s bandwidth and 2560 shading units allow the RDNA 2.0 card to process substantially more geometry and shading work per frame.

The second test, Geekbench OpenCL, reverses the outcome. The R9 M290X scores 22028 versus the RX 6750 XT's 16360, a 25.7% delta in favor of the older card. This is notable because the R9 M290X has fewer shading units, lower clocks, and older GCN 1.0 architecture. The OpenCL result suggests driver-level optimizations or workload characteristics that favor the GCN design's compute scheduling. The R9 M290X's 256-bit memory bus, though lower bandwidth, may benefit certain OpenCL kernels that are sensitive to memory latency or access patterns.

The RX 6750 XT wins one head-to-head test; the R9 M290X wins one. However, the magnitude of the RX 6750 XT's Metal victory dwarfs the R9 M290X's OpenCL margin. The 459.7% delta in Metal represents a generational leap, while the 25.7% OpenCL delta is a narrow, legacy-specific edge. Across the full benchmark suite, the RX 6750 XT's average of 26011 versus 23276 confirms its overall superiority. The gap in average score is 2735 points, about 11.8% higher for the RX 6750 XT, yet the two GPUs sit only three percentile points apart (71st versus 68th) due to the dense clustering of scores in that range.

The RX 6750 XT's other recorded benchmark scores reinforce its position: 2548 in 3DMark Steel Nomad DX12, 98089 in Geekbench Vulkan, 20700 in Passmark G3D, 9550 in Passmark GPU Compute, and 972 in Passmark G2D. The R9 M290X has no recorded scores in those tests, so direct comparison is limited to the two Geekbench entries. The RX 6750 XT's Passmark G3D score of 20700 and compute score of 9550 indicate strong rasterization and compute throughput, consistent with its 13.31 TFLOPS FP32 rating.

The R9 M290X's OpenCL result of 22028 is higher than its Metal result of 24524 on the RX 6750 XT's OpenCL score of 16360, but the R9 M290X cannot match the RX 6750 XT in any other recorded metric. Its nearest rival, the AMD Radeon RX 6600M, averages 23273 with a 0% delta, meaning the R9 M290X is essentially tied with a modern laptop GPU. The RX 6750 XT, by contrast, leads its nearest rival, the R9 M395X, by only 0.5%, indicating it sits at the top of a tight performance cluster. The data shows a clear hierarchy: the RX 6750 XT competes at the upper midrange tier, while the R9 M290X anchors the lower midrange.