AMD Radeon R9 M290X vs AMD Radeon RX 590 Comparison

The AMD Radeon RX 590 and AMD Radeon R9 M290X represent two very different eras of AMD graphics, separated by nearly five years of architectural evolution. The RX 590 is a desktop Polaris 30 part built for high-refresh 1080p gaming, while the R9 M290X is a mobile-first Neptune chip from the GCN 1.0 days, typically found in laptops via MXM modules. Benchmark data shows a decisive performance gap, but the specifics of how and why they differ matter for anyone comparing these end-of-life options.

FAQ

Q: How much faster is the RX 590 than the R9 M290X in the available benchmark data?

A: In the Geekbench Metal test, the RX 590 scores 48,407 points versus 24,524 for the R9 M290X. That is a 97.4% advantage for the RX 590, meaning it delivers nearly double the performance in this compute-oriented test.

Q: Which GPU has the higher overall benchmark percentile?

A: The RX 590 sits at the 70th percentile of all GPUs, while the R9 M290X is at the 68th percentile. Despite the massive head-to-head delta, both cards land in a similar percentile band because the R9 M290X has an additional OpenCL benchmark score (22,028) that the RX 590 lacks, and the percentile calculation includes a broader set of GPUs.

Q: What are the memory specifications of each card?

A: The RX 590 comes with 8 GB of GDDR5 on a 256-bit bus, delivering 256.0 GB/s of bandwidth. The R9 M290X has 4 GB of GDDR5 on the same 256-bit bus, but its bandwidth is only 153.6 GB/s. The RX 590 also runs its memory at 2000 MHz (8 Gbps effective) versus 1200 MHz (4.8 Gbps effective) on the R9 M290X.

Q: Which card has a higher transistor count and what process node is used?

A: The RX 590 packs 5,700 million transistors on GlobalFoundries' 12 nm process, with a die size of 232 mm². The R9 M290X uses 2,800 million transistors on TSMC's 28 nm process, with a die size of 212 mm². The RX 590 achieves a transistor density of 24.6M per mm², nearly double the R9 M290X's 13.2M per mm².

Q: How do the power requirements differ between the two?

A: The RX 590 has a TDP of 175 W and requires a 450 W suggested PSU, using a single 8-pin power connector and a dual-slot cooler. The R9 M290X has a much lower TDP of 100 W, uses no external power connectors, and comes as an MXM module, making it suitable for portable devices.

Q: What are the API support differences?

A: The RX 590 supports DirectX 12 (12_0), OpenGL 4.6, and Vulkan 1.3. The R9 M290X supports DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.170. The RX 590 has a more complete DirectX 12 feature set and a newer Vulkan version.

The Verdict

The data is unambiguous: the AMD Radeon RX 590 is the far more capable GPU. Its 97.4% lead in the Geekbench Metal benchmark over the R9 M290X is a generational leap, not an incremental improvement. If you are building a desktop system and have the power budget, the RX 590 is the only rational choice. It offers double the memory (8 GB vs 4 GB), more than double the bandwidth (256.0 GB/s vs 153.6 GB/s), and nearly triple the FP32 throughput (7.119 TFLOPS vs 2.304 TFLOPS).

The R9 M290X does have one practical advantage: its 100 W TDP and MXM form factor make it usable in laptops or compact systems where the 175 W dual-slot RX 590 would never fit. However, even in that niche, its performance is severely limited. The R9 M290X's nearest rival is the AMD Radeon RX 6600M with a deltaPct of 0, meaning it is essentially tied with that mobile GPU, but the RX 590 sits 1.2% ahead of the RX 6600 XT in its own rival list. The RX 590 is also 0.1% behind the NVIDIA RTX A5000 Mobile and 0.4% ahead of the Intel Arc A350M, showing it competes with much newer hardware despite its age.

For anyone who can physically install the RX 590, there is no argument for the R9 M290X. The only scenario where the R9 M290X wins is if the system requires a 100 W mobile module with no external power connector. Otherwise, the RX 590 dominates every measurable metric in the fact pack.

Head-to-Head Benchmarks

The only direct head-to-head benchmark available is Geekbench Metal, and the result is a landslide. The RX 590 scores 48,407 points, while the R9 M290X manages 24,524 points. The deltaPct of 97.4% means the RX 590 is nearly twice as fast. This is not a close contest; it is the difference between a playable modern experience and an obsolete one.

The RX 590 also wins the only recorded head-to-head victory (winsA: 1, winsB: 0). There is no benchmark in the fact pack where the R9 M290X comes out ahead. Beyond the direct comparison, the RX 590's average benchmark score of 24,744 is 6.3% higher than the R9 M290X's average of 23,276. That average gap is smaller than the Metal delta because the R9 M290X has an additional OpenCL score of 22,028, which drags its average down less than the Metal score alone would suggest.

Looking at the rival context, the RX 590's avgScore of 24,744 puts it just 0.1% below the NVIDIA RTX A5000 Mobile (24,763) and 0.4% above the Intel Arc A350M (24,647). The R9 M290X's avgScore of 23,276 is exactly tied with the AMD Radeon RX 6600M (23,273) and 0.1% ahead of the AMD Radeon Pro Vega 16 (23,250). This shows the RX 590 is competing in a higher performance tier entirely, despite being an older architecture.

Specification Differences

The core specification differences are stark. The RX 590 has 2,304 shading units, 144 TMUs, and 32 ROPs, while the R9 M290X has 1,280 shading units, 80 TMUs, and 32 ROPs. That is 80% more shading units and 80% more TMUs on the RX 590, with the same ROP count.

Clock speeds tell a similar story. The RX 590 runs at a base of 1469 MHz and boosts to 1545 MHz. The R9 M290X operates at a base of 850 MHz and a boost of 900 MHz. The RX 590's boost clock is 71.7% higher than the R9 M290X's boost clock.

Memory is another major differentiator. The RX 590 has 8 GB of GDDR5 at 2000 MHz (8 Gbps effective) for 256.0 GB/s bandwidth. The R9 M290X has 4 GB of GDDR5 at 1200 MHz (4.8 Gbps effective) for 153.6 GB/s bandwidth. Both use a 256-bit bus, but the RX 590's higher clock speed gives it 66.7% more bandwidth.

Pixel and texture rates follow the same pattern. The RX 590 achieves 49.44 GPixel/s and 222.5 GTexel/s, versus 28.80 GPixel/s and 72.00 GTexel/s for the R9 M290X. The RX 590 is 71.7% faster in pixel fill and 209% faster in texture fill.

Power and physical specs differ completely. The RX 590 is a dual-slot card, 241 mm (9.5 inches) long, with a 175 W TDP, 1x 8-pin connector, and a 450 W suggested PSU. The R9 M290X is an MXM module with a 100 W TDP, no power connectors, and no listed dimensions, making it a mobile-only solution.

Architecture Differences

The architectural gap is fundamental. The RX 590 uses the Polaris 30 chip on GCN 4.0 architecture, built on a 12 nm process at GlobalFoundries. The R9 M290X uses the Neptune chip on GCN 1.0 architecture, built on a 28 nm process at TSMC. Two full GCN generations separate them, which explains the massive efficiency and feature differences.

Transistor counts reflect the process advantage. The RX 590 has 5,700 million transistors on a 232 mm² die, giving a density of 24.6M per mm². The R9 M290X has 2,800 million transistors on a 212 mm² die, giving a density of 13.2M per mm². The RX 590 crams more than twice the transistors into a die that is only 9.4% larger, a direct result of the 12 nm vs 28 nm process gap.

The FP32 compute output confirms the architectural leap. The RX 590 delivers 7.119 TFLOPS, more than triple the R9 M290X's 2.304 TFLOPS. The RX 590 also supports FP16 at 7.119 TFLOPS (1:1), while the R9 M290X has no listed FP16 capability.

API support differs as well. The RX 590 supports DirectX 12 (12_0), giving it the full feature set for modern games. The R9 M290X only supports DirectX 12 (11_1), which lacks some of the newer rendering features. Vulkan support is also newer on the RX 590 (1.3 vs 1.2.170). Both support OpenGL 4.6.

Display outputs are another architectural consequence. The RX 590 offers 1x HDMI 2.0b and 3x DisplayPort 1.4a, suitable for desktop multi-monitor setups. The R9 M290X's outputs are "Portable Device Dependent," meaning they vary by laptop implementation. The RX 590 also has a listed 241 mm length, while the R9 M290X has no dimensions listed.

The release dates bracket the difference: the R9 M290X launched in January 2014, and the RX 590 in November 2018. Both are now end-of-life products, but the RX 590's successor is listed as Vega, while the R9 M290X's successor is Polaris Mobile, which is the family the RX 590 belongs to.

Where Each One Wins

The RX 590 wins everywhere performance matters. In the Geekbench Metal test, it is 97.4% faster. It has double the memory capacity, 66.7% more memory bandwidth, 80% more shading units, 80% more TMUs, and 209% more texture fill rate. Its FP32 compute is 3.1 times higher. For any gaming or compute workload that fits within its 175 W power envelope, the RX 590 is the clear winner.

The R9 M290X's only wins are in portability and power efficiency. Its 100 W TDP is 42.9% lower than the RX 590's 175 W. Its MXM form factor and lack of power connectors make it installable in laptops, where the RX 590's dual-slot 241 mm design would never fit. The R9 M290X also has no suggested PSU requirement, making it suitable for systems with limited power delivery.

For a desktop user, the RX 590 is the obvious pick. Its 8 GB of VRAM is sufficient for modern game textures, and its 256.0 GB/s bandwidth and 7.119 TFLOPS FP32 handle 1080p gaming well. Its nearest rivals include the NVIDIA RTX A5000 Mobile and Intel Arc A350M, putting it in a competitive position even against newer hardware.

For a laptop user, the R9 M290X is the only option of the two, but it is a weak one. Its 4 GB VRAM and 153.6 GB/s bandwidth will struggle with modern titles, and its 2.304 TFLOPS FP32 is barely a third of the RX 590's output. Its nearest rival is the AMD Radeon RX 6600M, a mobile GPU, and it is exactly tied with it, meaning the R9 M290X is not even competitive within its own mobile class in this data.

The verdict is simple: the RX 590 wins on every performance metric, and the R9 M290X wins only on power draw and form factor. Choose the RX 590 for desktops, and only consider the R9 M290X if the system physically requires a 100 W MXM module.