AMD Radeon RX 9060 XT LP vs NVIDIA GeForce RTX 4070 GDDR6 Comparison
AMD Radeon RX 9060 XT LP
GeForce RTX 4070 GDDR6
PERFORMANCE BENCHMARKS
Analysis: AMD Radeon RX 9060 XT LP vs NVIDIA GeForce RTX 4070 GDDR6
AMD Radeon RX 9060 XT LP and NVIDIA GeForce RTX 4070 GDDR6 occupy very different positions in the database’s performance hierarchy. The AMD card, built on the RDNA 4.0 architecture with a 4 nm process, records an average benchmark score of 63830 and sits in the 89th percentile of all GPUs. The NVIDIA card, using Ada Lovelace on a 5 nm process, records an average score of 4335 and sits in the 25th percentile. These averages, however, come from different benchmark suites, so the head-to-head comparison must rely on the specific recorded tests rather than a direct score ratio.
Head-to-Head Benchmarks
The database contains no shared benchmark tests between the AMD Radeon RX 9060 XT LP and the NVIDIA GeForce RTX 4070 GDDR6. The AMD card has two recorded results: Geekbench OpenCL at 88183 and Geekbench Vulkan at 39476. The NVIDIA card has one recorded result: 3DMark Steel Nomad DX12 at 4334.5. Because no test appears in both cards’ result sets, a direct apples-to-apples comparison is not possible from the recorded data.
The AMD card’s average benchmark score of 63830 places it in the 89th percentile of all GPUs in the database. Its nearest rivals by average score are the NVIDIA CMP 30HX at 63842, which is effectively identical with a delta of 0 percent, the AMD Radeon RX 7600M at 63775, which trails by 0.1 percent, and the AMD Radeon Pro Vega 56 at 63693, which trails by 0.2 percent. The AMD Radeon Pro WX 9100 leads the AMD card by 0.6 percent with a score of 64212. These deltas show the RX 9060 XT LP sits in a tightly packed cluster of GPUs, where a 0.1 percent swing changes the ranking order. Its individual Geekbench OpenCL score of 88183 is substantially higher than its Vulkan score of 39476, indicating that the card’s compute performance under OpenCL is far ahead of its Vulkan performance in the database’s measurements.
The NVIDIA GeForce RTX 4070 GDDR6, with an average score of 4335, sits in the 25th percentile. Its nearest rivals are all older or entry-level parts: the Intel Iris Pro Graphics 5200 leads by 0.6 percent with a score of 4360, the AMD FirePro W2100 trails by 0.9 percent with a score of 4295, the NVIDIA GeForce 930M leads by 1.2 percent with a score of 4388, and the NVIDIA GeForce GTX 460M trails by 1.2 percent with a score of 4282. The 3DMark Steel Nomad DX12 score of 4334.5 is the only benchmark recorded for this card, and its percentile ranking reflects that single test. The data shows the RTX 4070 GDDR6 is not an outlier in either direction; it sits within 1.2 percent of all four nearest rivals.
Because the two cards’ benchmark results come from different tests, the database cannot confirm which card is faster in any shared workload. The AMD card’s average score is over fourteen times higher than the NVIDIA card’s average, but that gap reflects the differing benchmark suites, not a direct performance comparison. The head-to-head benchmark section in the database is empty, with zero wins recorded for either card.
Architecture Differences
The AMD Radeon RX 9060 XT LP uses the Navi 44 chip with the RDNA 4.0 architecture, manufactured on a 4 nm process at TSMC. It contains 29,700 million transistors on a 199 mm² die, giving a transistor density of 149.2 million per mm². The NVIDIA GeForce RTX 4070 GDDR6 uses the AD104 chip with the Ada Lovelace architecture, also manufactured at TSMC but on a 5 nm process. It contains 35,800 million transistors on a 294 mm² die, giving a transistor density of 121.8 million per mm². The AMD chip has fewer transistors overall but packs them more densely on a smaller die.
The AMD card’s compute configuration includes 2048 shading units, 128 texture mapping units, and 64 raster operation pipelines. It has 32 ray tracing cores and no tensor cores listed. The NVIDIA card has 5888 shading units, 184 texture mapping units, and 64 raster operation pipelines. It has 46 ray tracing cores and 184 tensor cores. The NVIDIA card has nearly three times the shading units and nearly double the ray tracing cores, plus a dedicated tensor core array that the AMD card lacks entirely.
Memory configurations differ sharply. The AMD card uses 16 GB of GDDR6 on a 128 bit bus, delivering 322.3 GB/s of bandwidth. The NVIDIA card uses 12 GB of GDDR6 on a 192 bit bus, delivering 480.0 GB/s of bandwidth. The NVIDIA card has a wider memory bus and higher bandwidth, while the AMD card has 4 GB more capacity. The AMD card’s memory clock is listed at 2518 MHz with 20.1 Gbps effective, while the NVIDIA card’s memory clock is 2500 MHz with 20 Gbps effective, so the raw memory clock rates are nearly identical.
Clock speeds also differ. The AMD card has a base clock of 1380 MHz, a boost clock of 3050 MHz, and a game clock of 2450 MHz. The NVIDIA card has a base clock of 1920 MHz and a boost clock of 2475 MHz, with no game clock listed. The AMD card’s boost clock is considerably higher, but its base clock is much lower. The AMD card’s processing rates are 195.2 GPixel/s pixel rate and 390.4 GTexel/s texture rate, while the NVIDIA card’s are 158.4 GPixel/s and 455.4 GTexel/s. The AMD card leads in pixel throughput, the NVIDIA card leads in texture throughput. The AMD card’s FP32 compute is 24.99 TFLOPS and its FP16 is 24.99 TFLOPS at a 1:1 ratio. The NVIDIA card’s FP32 is 29.15 TFLOPS and its FP16 is also 29.15 TFLOPS at 1:1, giving the NVIDIA card a lead in raw shader compute.
The AMD card is built on PCIe 5.0 x16, while the NVIDIA card uses PCIe 4.0 x16. The NVIDIA card has a lower power draw at 200 W TDP versus the AMD card’s 140 W TDP, and the NVIDIA card requires a 550 W suggested power supply versus the AMD card’s 300 W. The NVIDIA card uses a single 16-pin power connector, the AMD card uses a single 8-pin connector. Both are dual-slot cards. The AMD card’s display outputs are one HDMI 2.1b and two DisplayPort 2.1a. The NVIDIA card’s outputs are one HDMI 2.1 and three DisplayPort 1.4a. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.
The NVIDIA card has physical dimensions listed: 240 mm length, 110 mm height, and 40 mm width. The AMD card has no dimensions recorded in the database. The AMD card is listed as active in production status, while the NVIDIA card is end-of-life. The AMD card released on 2025-12-16, the NVIDIA card on 2024-08-19.
The Verdict
The recorded data supports a clear split between these two cards, but not a head-to-head winner, because no shared benchmark exists. The AMD Radeon RX 9060 XT LP is the stronger candidate on average benchmark score and percentile placement. Its average of 63830 places it in the 89th percentile, and its nearest rivals all sit within 0.6 percent of its score, showing it competes at a high level among the database’s GPU population. Its 16 GB memory capacity is double the NVIDIA card’s 12 GB, and its smaller 140 W TDP makes it a lighter power load with a lower suggested power supply of 300 W versus 550 W.
The NVIDIA GeForce RTX 4070 GDDR6 is the stronger candidate on raw shader compute and memory bandwidth. Its FP32 throughput of 29.15 TFLOPS exceeds the AMD card’s 24.99 TFLOPS, its texture rate of 455.4 GTexel/s exceeds the AMD card’s 390.4 GTexel/s, and its memory bandwidth of 480.0 GB/s exceeds the AMD card’s 322.3 GB/s. It also has 184 tensor cores, which the AMD card does not have, and 46 ray tracing cores versus 32. However, its average benchmark score of 4335 and 25th percentile placement are far below the AMD card’s, and its nearest rivals are integrated and mobile graphics parts from previous generations.
The AMD card is the data-backed choice for anyone prioritizing overall database performance ranking, memory capacity, and power efficiency. The NVIDIA card is the data-backed choice for anyone prioritizing compute throughput, texture processing, memory bandwidth, and tensor core availability. The absence of a shared benchmark means the database cannot declare one card faster in a common workload.
Specification Differences
| Specification | AMD Radeon RX 9060 XT LP | NVIDIA GeForce RTX 4070 GDDR6 |
| --- | --- | --- |
| Architecture | RDNA 4.0 | Ada Lovelace |
| Process node | 4 nm | 5 nm |
| Transistors | 29,700 million | 35,800 million |
| Die size | 199 mm² | 294 mm² |
| Transistor density | 149.2M / mm² | 121.8M / mm² |
| Base clock | 1380 MHz | 1920 MHz |
| Boost clock | 3050 MHz | 2475 MHz |
| Game clock | 2450 MHz | None |
| Memory size | 16 GB | 12 GB |
| Memory bus width | 128 bit | 192 bit |
| Memory bandwidth | 322.3 GB/s | 480.0 GB/s |
| Shading units | 2048 | 5888 |
| TMUs | 128 | 184 |
| ROPs | 64 | 64 |
| Ray tracing cores | 32 | 46 |
| Tensor cores | None | 184 |
| Pixel rate | 195.2 GPixel/s | 158.4 GPixel/s |
| Texture rate | 390.4 GTexel/s | 455.4 GTexel/s |
| FP32 | 24.99 TFLOPS | 29.15 TFLOPS |
| FP16 | 24.99 TFLOPS (1:1) | 29.15 TFLOPS (1:1) |
| TDP | 140 W | 200 W |
| Power connector | 1x 8-pin | 1x 16-pin |
| Suggested PSU | 300 W | 550 W |
| Bus interface | PCIe 5.0 x16 | PCIe 4.0 x16 |
| Display outputs | 1x HDMI 2.1b, 2x DisplayPort 2.1a | 1x HDMI 2.1, 3x DisplayPort 1.4a |
| Production status | Active | End-of-life |
| Release date | 2025-12-16 | 2024-08-19 |
| Predecessor | Navi III | GeForce 30 |
| Successor | None | GeForce 50 |
| Launch MSRP | None | 599 USD |
FAQ
Q: Which card has the higher average benchmark score?
A: The AMD Radeon RX 9060 XT LP has an average benchmark score of 63830, while the NVIDIA GeForce RTX 4070 GDDR6 has an average score of 4335.
Q: How do the two cards compare in memory capacity and bandwidth?
A: The AMD card has 16 GB of GDDR6 on a 128 bit bus with 322.3 GB/s bandwidth. The NVIDIA card has 12 GB of GDDR6 on a 192 bit bus with 480.0 GB/s bandwidth.
Q: What is the difference in power consumption?
A: The AMD card has a 140 W TDP and a suggested power supply of 300 W. The NVIDIA card has a 200 W TDP and a suggested power supply of 550 W.
Q: Does the NVIDIA card have tensor cores?
A: Yes, the NVIDIA GeForce RTX 4070 GDDR6 has 184 tensor cores. The AMD card has no tensor cores listed in the database.
Q: Which card has more ray tracing cores?
A: The NVIDIA card has 46 ray tracing cores, while the AMD card has 32.
Q: What benchmark results are recorded for each card?
A: The AMD card has a Geekbench OpenCL score of 88183 and a Geekbench Vulkan score of 39476. The NVIDIA card has a 3DMark Steel Nomad DX12 score of 4334.5.
Where Each One Wins
The AMD Radeon RX 9060 XT LP wins on overall database placement. Its 89th percentile rank and average score of 63830 place it among the top tier of the GPU population, and its nearest rivals are all within 0.6 percent. It also wins on memory capacity, offering 16 GB versus 12 GB, and on pixel throughput, with 195.2 GPixel/s versus 158.4 GPixel/s. Its boost clock of 3050 MHz is higher than the NVIDIA card’s 2475 MHz, and its transistor density of 149.2 million per mm² is higher than the NVIDIA card’s 121.8 million per mm². It draws less power at 140 W versus 200 W, needs a 300 W power supply instead of 550 W, uses PCIe 5.0 x16 instead of PCIe 4.0 x16, and is listed as active in production. Its launch MSRP is not recorded in the database.
The NVIDIA GeForce RTX 4070 GDDR6 wins on raw compute and bandwidth. Its FP32 throughput of 29.15 TFLOPS beats the AMD card’s 24.99 TFLOPS, and its FP16 throughput matches at 29.15 TFLOPS versus 24.99 TFLOPS. Its texture rate of 455.4 GTexel/s beats the AMD card’s 390.4 GTexel/s, and its memory bandwidth of 480.0 GB/s beats the AMD card’s 322.3 GB/s. It has more shading units at 5888 versus 2048, more texture mapping units at 184 versus 128, more ray tracing cores at 46 versus 32, and 184 tensor cores where the AMD card has none. Its base clock of 1920 MHz is higher than the AMD card’s 1380 MHz. Its launch MSRP is 599 USD. It is end-of-life, with the GeForce 50 series listed as its successor.