AMD Radeon RX 7800M vs NVIDIA GeForce RTX 5090 SE Comparison
AMD Radeon RX 7800M
GeForce RTX 5090 SE
PERFORMANCE BENCHMARKS
Analysis: AMD Radeon RX 7800M vs NVIDIA GeForce RTX 5090 SE
Head-to-Head Benchmarks
The benchmark database contains no direct head-to-head results between the AMD Radeon RX 7800M and the NVIDIA GeForce RTX 5090 SE. The RX 7800M has a complete set of recorded scores, while the RTX 5090 SE has no benchmark entries at all. This asymmetry makes a traditional score-by-score comparison impossible.
The RX 7800M posts an average benchmark score of 27,883 across ten tests. Its strongest results appear in compute-oriented workloads: Geekbench Vulkan returns 126,668, Geekbench OpenCL returns 120,778, and Passmark GPU Compute returns 9,342. In DirectX gaming tests, the card scores 176 in Passmark DirectX 11, 99 in DirectX 10, and 89 in DirectX 12. The 3DMark Steel Nomad DX12 test records 2,994 points. Passmark G3D adds 17,613, while the 2D score sits at 892.
The RX 7800M holds the 73rd percentile among all GPUs in the database. Its nearest rivals by average score are the AMD Radeon Pro Vega 20 at 27,839 (0.2% ahead), the AMD Radeon Pro W5500X at 27,973 (0.3% behind), the NVIDIA GeForce GTX 980 Ti at 28,020 (0.5% behind), and the AMD FirePro S7150 at 28,117 (0.8% behind). The data shows the RX 7800M sits within 1% of each of these cards, indicating a tightly clustered performance band rather than a clear win over any direct competitor.
For the RTX 5090 SE, the database records zero benchmarks, an average score of zero, and a 50th percentile ranking. With no measured results, the database cannot confirm any performance advantage for either card. The RTX 5090 SE's 50th percentile is a default placeholder, not a measured outcome. Any claim about relative speed would require speculation, which the recorded data does not support.
Architecture Differences
The two GPUs diverge fundamentally in architecture generation and implementation. The AMD Radeon RX 7800M uses the Navi 32 chip based on RDNA 3.0, codenamed Wheat Nas, and belongs to the Navi Mobile (RX 7000M) generation. The NVIDIA GeForce RTX 5090 SE uses the GB202 chip based on Blackwell 2.0 and belongs to the GeForce 50 generation. Both are manufactured by TSMC on a 5 nm process, but the transistor counts differ sharply: the RX 7800M packs 28,100 million transistors on a 346 mm² die, yielding a density of 81.2 million transistors per mm². The RTX 5090 SE scales to 92,200 million transistors on a 750 mm² die, for a density of 122.9 million per mm². That represents a 3.3x transistor advantage for the NVIDIA part.
Core configurations reflect the size gap. The RX 7800M has 3,840 shading units, 240 texture mapping units, 96 ROPs, 60 ray tracing cores, and no tensor cores. The RTX 5090 SE has 14,080 shading units, 440 TMUs, 160 ROPs, 110 ray tracing cores, and 440 tensor cores. The NVIDIA card therefore carries roughly 3.7x the shading units, 1.8x the TMUs, 1.7x the ROPs, and 1.8x the ray tracing cores. The presence of 440 tensor cores on the RTX 5090 SE marks a categorical difference: the RX 7800M has no tensor core hardware at all, which affects AI acceleration and DLSS-type workloads, though the database records no specific tests for those features.
Memory architecture also differs. The RX 7800M uses 12 GB of GDDR6 on a 192-bit bus, achieving 432.0 GB/s of bandwidth. The RTX 5090 SE uses 24 GB of GDDR7 on a 384-bit bus, achieving 1.34 TB/s. That is roughly 3.1x the memory capacity and 3.1x the bandwidth. Clock behavior shows a mixed picture. The RX 7800M runs at a 1295 MHz base, a 2145 MHz game clock, and a 2335 MHz boost, with memory at 2250 MHz (18 Gbps effective). The RTX 5090 SE runs at a 1740 MHz base and a 2377 MHz boost, with memory at 1750 MHz (28 Gbps effective). The NVIDIA part has higher base and boost clocks, while the AMD part has a higher memory clock in MHz terms, though the effective data rate is higher on the NVIDIA card.
Compute throughput follows the core counts. The RX 7800M delivers 35.87 TFLOPS for both FP32 and FP16, with a texture rate of 560.4 GTexel/s and a pixel rate of 224.2 GPixel/s. The RTX 5090 SE delivers 66.94 TFLOPS for FP32 and FP16, a texture rate of 1,045.9 GTexel/s, and a pixel rate of 380.3 GPixel/s. The NVIDIA card roughly doubles FP32 throughput, nearly doubles texture rate, and exceeds pixel rate by about 70%.
Power and physical design diverge substantially. The RX 7800M has a TDP of 180 W, an IGP slot width, no power connectors, and portable-device-dependent display outputs. It is designed for mobile integration. The RTX 5090 SE has a TDP of 500 W, a dual-slot width, a single 16-pin power connector, a suggested PSU of 900 W, and measures 267 mm by 111 mm by 40 mm. The database lists no length or height for the RX 7800M. The RTX 5090 SE also uses PCIe 5.0 x16, while the RX 7800M uses PCIe 4.0 x16. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.
FAQ
Q: Which GPU has a higher average benchmark score in the database?
A: The AMD Radeon RX 7800M has an average benchmark score of 27,883. The NVIDIA GeForce RTX 5090 SE has an average score of zero because no benchmarks are recorded for it.
Q: How does the RX 7800M compare to its nearest rivals?
A: The RX 7800M sits within 1% of four rivals: the AMD Radeon Pro Vega 20 (0.2% ahead), the AMD Radeon Pro W5500X (0.3% behind), the NVIDIA GeForce GTX 980 Ti (0.5% behind), and the AMD FirePro S7150 (0.8% behind).
Q: What are the memory capacities and types of each card?
A: The RX 7800M has 12 GB of GDDR6 on a 192-bit bus with 432.0 GB/s bandwidth. The RTX 5090 SE has 24 GB of GDDR7 on a 384-bit bus with 1.34 TB/s bandwidth.
Q: Does either card have tensor cores?
A: No. The RX 7800M has no tensor cores. The RTX 5090 SE has 440 tensor cores, which the RX 7800M lacks entirely.
Q: What is the TDP difference between the two cards?
A: The RX 7800M has a TDP of 180 W. The RTX 5090 SE has a TDP of 500 W, a 320 W difference.
Q: Which card has a higher boost clock?
A: The RTX 5090 SE boosts to 2377 MHz, while the RX 7800M boosts to 2335 MHz, a 42 MHz difference in favor of the NVIDIA card.
Specification Differences
| Specification | AMD Radeon RX 7800M | NVIDIA GeForce RTX 5090 SE |
|---|---|---|
| Chip | Navi 32 | GB202 |
| Architecture | RDNA 3.0 | Blackwell 2.0 |
| Generation | Navi Mobile (RX 7000M) | GeForce 50 |
| Transistors | 28,100 million | 92,200 million |
| Die Size | 346 mm² | 750 mm² |
| Transistor Density | 81.2M / mm² | 122.9M / mm² |
| Base Clock | 1295 MHz | 1740 MHz |
| Boost Clock | 2335 MHz | 2377 MHz |
| Game Clock | 2145 MHz | null |
| Memory Clock | 2250 MHz (18 Gbps effective) | 1750 MHz (28 Gbps effective) |
| Memory Size | 12 GB | 24 GB |
| Memory Type | GDDR6 | GDDR7 |
| Memory Bus Width | 192 bit | 384 bit |
| Memory Bandwidth | 432.0 GB/s | 1.34 TB/s |
| Shading Units | 3840 | 14080 |
| TMUs | 240 | 440 |
| ROPs | 96 | 160 |
| RT Cores | 60 | 110 |
| Tensor Cores | null | 440 |
| Pixel Rate | 224.2 GPixel/s | 380.3 GPixel/s |
| Texture Rate | 560.4 GTexel/s | 1,045.9 GTexel/s |
| FP32 | 35.87 TFLOPS | 66.94 TFLOPS |
| FP16 | 35.87 TFLOPS (1:1) | 66.94 TFLOPS (1:1) |
| TDP | 180 W | 500 W |
| Slot Width | IGP | Dual-slot |
| Power Connectors | None | 1x 16-pin |
| Suggested PSU | null | 900 W |
| Bus Interface | PCIe 4.0 x16 | PCIe 5.0 x16 |
| Display Outputs | Portable Device Dependent | 1x HDMI 2.1b, 3x DisplayPort 2.1b |
| Dimensions | null | 267 mm x 111 mm x 40 mm |
| Release Date | 2024-09-10 | 2025-12-31 |
| Predecessor | Polaris Mobile | GeForce 40 |
| Successor | null | GeForce 60 |
| Launch MSRP | null | 1,499 USD |
The two cards share identical API support: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Both are produced by TSMC on a 5 nm process. Both have active production status. The release dates differ by over a year, with the RX 7800M launching on 2024-09-10 and the RTX 5090 SE on 2025-12-31.
The Verdict
The recorded data presents a clear asymmetry. The AMD Radeon RX 7800M is a fully measured product: ten benchmark entries, an average score of 27,883, and a 73rd percentile ranking. It competes within a narrow band around the 28,000 average-score mark, where its nearest rivals sit between 27,839 and 28,117. The NVIDIA GeForce RTX 5090 SE has no benchmark results, no average score, and a 50th percentile that reflects missing data rather than measured performance. The database cannot verify any performance claim for the RTX 5090 SE.
For users who require immediate, database-confirmed gaming and compute scores, the RX 7800M is the only card with evidence. Its 12 GB GDDR6 memory, 35.87 TFLOPS FP32 throughput, and 180 W TDP suit a mobile platform with an IGP form factor and no external power connectors. The RTX 5090 SE, by contrast, is a dual-slot desktop card with a 500 W TDP, a 900 W suggested PSU, and a 1,499 USD launch MSRP. Its 24 GB GDDR7 memory, 66.94 TFLOPS FP32, and 440 tensor cores indicate a far larger hardware envelope, but the database contains no measurements to confirm how that envelope translates into benchmark results.
The architecture comparison favors the RTX 5090 SE on paper: more transistors, more shading units, more memory, more bandwidth, and double the FP32 throughput. The RX 7800M counters with a lower power draw, a mobile-friendly IGP design, and a release date nearly 16 months earlier. Neither card has a head-to-head benchmark entry, and the RTX 5090 SE has no standalone entries either. Based strictly on recorded data, the RX 7800M is the only card with demonstrated performance, while the RTX 5090 SE remains an unmeasured specification sheet. The verdict from the database: choose the RX 7800M if verified benchmark scores are required; choose the RTX 5090 SE only if raw architectural specifications and a later release date carry more weight than measured results.