AMD Radeon HD 7790 vs NVIDIA GeForce RTX 3060 Ti Comparison

FAQ

Q: How do the two cards compare in raw benchmark scores?

A: The AMD Radeon HD 7790 has an average benchmark score of 17,666, while the NVIDIA GeForce RTX 3060 Ti averages 16,129. Despite the HD 7790 being an older, lower-tier product, its recorded average is higher by about 9.5% in the database.

Q: Which card has better API support for modern games?

A: The RTX 3060 Ti supports DirectX 12 Ultimate (12_2), while the HD 7790 only reaches DirectX 12 (12_0). The RTX card also supports Vulkan 1.4 versus Vulkan 1.2.170 on the AMD card. This makes the RTX 3060 Ti more forward-compatible for feature-heavy titles.

Q: What are the memory capacities and types?

A: The HD 7790 has 1 GB of GDDR5 on a 128-bit bus, yielding 96.00 GB/s bandwidth. The RTX 3060 Ti has 8 GB of GDDR6 on a 256-bit bus, giving 448.0 GB/s bandwidth. The difference in memory size and bandwidth is substantial.

Q: Are these cards still in production?

A: No. Both are marked as End-of-life in the database. The HD 7790 was released in March 2013, and the RTX 3060 Ti was released in November 2020.

Q: Which card has ray tracing and tensor cores?

A: Only the RTX 3060 Ti has them, with 38 RT cores and 152 tensor cores. The HD 7790 has no dedicated RT or tensor hardware, so it cannot offload ray tracing or AI workloads in the same way.

Q: What is the power requirement difference?

A: The HD 7790 has a TDP of 85 W and a suggested PSU of 250 W with a single 6-pin connector. The RTX 3060 Ti has a TDP of 200 W and a suggested PSU of 550 W with a single 12-pin connector. The newer NVIDIA card demands more power and a stronger power supply.

Architecture Differences

The AMD Radeon HD 7790 is built on the Bonaire chip using GCN 2.0 architecture, manufactured on a 28 nm process at TSMC. It belongs to the Southern Islands generation (HD 7700 series). The NVIDIA GeForce RTX 3060 Ti uses the GA104 chip with Ampere architecture, built on an 8 nm process at Samsung, and belongs to the GeForce 30-series. The process node difference is a major generational leap, with transistor counts reflecting that shift.

The HD 7790 packs 2,080 million transistors on a 392 mm² die, giving a density of 13.0M / mm². The RTX 3060 Ti holds 17,400 million transistors on a larger 392 mm² die, achieving a density of 44.4M / mm². The NVIDIA card packs many more units: 4,864 shading units, 152 TMUs, and 80 ROPs for the RTX card, compared to 896 shading units, 56 TMUs, and 16 ROPs on the AMD card. Compute output scales accordingly.

The HD 7790 has no RT cores, tensor cores, or hardware for ray tracing, while the RTX 3060 Ti includes 38 RT cores and 152 tensor cores. The RTX card also supports FP16 at 16.20 TFLOPS (1:1), whereas the HD 7790 does not list an FP16 figure. FP32 performance is 1.792 TFLOPS for the AMD card versus 16. The RTX 3060 Ti's 16.2 TFLOPS is roughly 9x higher in that metric.

Memory architecture differs fundamentally. The HD 7790 uses 1 GB of GDDR5 with a 128-bit bus. The RTX 3060 Ti uses 8 GB of GDDR6 on a 256-bit bus. Pixel rate for the RTX card is 133.2 GPixel/s versus 16.00 GPixel/s on the AMD card. Texture rate is 253.1 GTexel/s for the NVIDIA card versus 56.00 GTexel/s for the AMD card. Memory clock is 1500 MHz (6 Gbps effective) on the HD 7790 and 1750 MHz (14 Gbps effective) on the RTX 3060 Ti.

The RTX 3060 Ti also supports PCIe 4.0 x16, while the HD 7790 uses PCIe 3.0 x16. Display outputs differ as well: the HD 7790 has 1x DVI, 1x HDMI 1.4a, and 2x mini-DisplayPort 1.2, while the RTX 3060 Ti has 1x HDMI 2.1 and 3x DisplayPort 1.4a. The RTX card has a base clock of 1410 MHz and a boost of 1665 MHz, while the HD 7790 does not list base or boost clocks.

Head-to-Head Benchmarks

The database does not include direct head-to-head benchmark results between these two cards. Instead, the HD 7790 has one recorded benchmark (Geekbench Metal) scoring 17,666, while the RTX 3060 Ti has multiple scores across different tests.

In Geekbench Metal, the HD 7790 scores 17,666. Its nearest rivals in the database are the NVIDIA GeForce RTX 4060 at 17,639 (0.2% slower), the AMD Radeon 780M at 17,588 (0.4% slower), the AMD Radeon Pro 560 at 17,551 (0.7% slower), and the NVIDIA Quadro RTX 4000 at 17,789 (0.7% faster). This places the HD 7790 in a competitive mid-range cluster where small margins separate cards.

The RTX 3060 Ti's Geekbench OpenCL score is 78,927, and its Geekbench Vulkan score is 47,784. Its nearest rivals include the AMD Radeon RX 9060 at 16,014 (0.7% faster than the RTX card's average), the AMD Radeon Pro 5600M at 16,351 (1.4% faster), and the AMD Radeon RX 5700 XT at 16,361 (1.4% faster). The AMD Radeon R9 370X trails at 15,862, which is 1.7% slower.

The RTX 3060 Ti also shows strong results in PassMark tests: 3D Mark Steel Nomad DX12 score of 2,626, PassMark G3D of 20,349, PassMark GPU Compute of 10,006, and PassMark G2D of 989. Its DirectX 9 score is 234, DirectX 10 is 132, DirectX 11 is 163, and DirectX 12 is 78. These scores are not directly comparable to the HD 7790 because the AMD card lacks corresponding entries in the database.

The percentile rankings show the HD 7790 at the 61st percentile of all GPUs, while the RTX 3060 Ti sits at the 59th percentile. Despite the RTX card having far more compute units, higher bandwidth, and newer architecture, the HD 7790 edges out a higher percentile placement in this dataset. This is likely due to the specific benchmark mix recorded for each card.

The average benchmark score for the RTX 3060 Ti is 16,129, which is lower than the HD 7790's single-score average of 17,666. However, the RTX card's average is pulled down by its PassMark DirectX 12 score of 78 and other low sub-scores. The HD 7790 has only one recorded test, so its average reflects just that Metal result.

Specification Differences

Clock speeds: The RTX 3060 Ti lists a base clock of 1410 MHz and boost clock of 1665 MHz. The HD 7790 does not list base or boost clocks, only a memory clock of 1500 MHz (6 Gbps effective). The RTX card's memory clock is 1750 MHz (14 Gbps effective).

Memory: The HD 7790 has 1024 MB of GDDR5 with a 128-bit bus and 96.00 GB/s bandwidth. The RTX 3060 Ti has 8 GB of GDDR6 with a 256-bit bus and 448.0 GB/s bandwidth.

Compute units: The HD 7790 has 896 shading units, 56 TMUs, and 16 ROPs. The RTX 3060 Ti has 4,864 shading units, 152 TMUs, and 80 ROPs. The RTX card also has 38 RT cores and 152 tensor cores; the HD 7790 has none.

Performance rates: The HD 7790 achieves 16.00 GPixel/s and 56.00 GTexel/s, with 1.792 TFLOPS FP32. The RTX 3060 Ti achieves 133.2 GPixel/s and 253.1 GTexel/s, with 16.20 TFLOPS FP32 and 16.20 TFLOPS FP16.

Power and dimensions: TDP is 85 W for the HD 7790 versus 200 W for the RTX 3060 Ti. The HD 7790 uses a 250 W suggested PSU and a single 6-pin connector. The RTX card needs a 550 W suggested PSU and a single 12-pin connector. The HD 7790 is 183 mm long, while the RTX 3060 Ti is 242 mm long and 112 mm high. Both are dual-slot cards.

Interface and outputs: The HD 7790 uses PCIe 3.0 x16, while the RTX 3060 Ti uses PCIe 4.0 x16. Display outputs are 1x DVI, 1x HDMI 1.4a, 2x mini-DisplayPort 1.2 for the AMD card, and 1x HDMI 2.1, 3x DisplayPort 1.4a for the NVIDIA card.

API support: The HD 7790 supports DirectX 12 (12_0), OpenGL 4.6, and Vulkan 1.2.170. The RTX 3060 Ti supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Process and die: The HD 7790 is on a 28 nm TSMC process with 2,080 million transistors and a 160 mm² die. The RTX 3060 Ti is on an 8 nm Samsung process with 17,400 million transistors and a 392 mm² die. Transistor density is 13.0M / mm² versus 44.4M / mm².

Release and pricing: The HD 7790 launched on 2013-03-21 with a launch MSRP of 149 USD. The RTX 3060 Ti launched on 2020-11-30 with a launch MSRP of 399 USD. The HD 7790's predecessor is Northern Islands and successor is Sea Islands. The RTX 3060 Ti's predecessor is GeForce 20 and successor is GeForce 40.

The Verdict

The data tells a clear story about generational differences. The RTX 3060 Ti is the more capable card in nearly every technical specification: 4.4x more shading units, 2.7x more TMUs, 5x more ROPs, 8x more memory, and 4.7x more memory bandwidth. Its FP32 output of 16.20 TFLOPS dwarfs the HD 7790's 1.792 TFLOPS by a factor of about 9.

However, the HD 7790 holds a higher percentile ranking (61st versus 59th) and a higher average benchmark score (17,666 versus 16,129) in the database. This is because the two cards are measured with different benchmark suites. The HD 7790's single Geekbench Metal score is its only data point, while the RTX 3060 Ti's average includes lower PassMark sub-scores that drag down its mean.

For a practical builder, the RTX 3060 Ti is the clear choice for modern workloads. It has 8 GB of GDDR6 memory versus 1 GB of GDDR5, which alone makes the HD 7790 unsuitable for contemporary gaming or content creation. The RTX card adds hardware ray tracing, tensor cores, and DirectX 12 Ultimate support, none of which exist on the HD 7790.

The HD 7790 is an end-of-life product from 2013. Its 85 W TDP and 250 W suggested PSU make it a low-power card, but its 1 GB memory cap and lack of modern features limit it to legacy or very light use cases. The RTX 3060 Ti, while also end-of-life, is a much more recent and capable product. The launch MSRP difference of 149 USD versus 399 USD reflects the performance gap.

Where Each One Wins

AMD Radeon HD 7790 wins on efficiency and compactness. It draws 85 W versus 200 W, needs only a 250 W PSU versus 550 W, and measures 183 mm versus 242 mm. For a small form factor build or a system with a weak power supply, the HD 7790 is far easier to accommodate. Its single 6-pin connector is also more compatible with older power supplies than the RTX card's 12-pin connector.

AMD Radeon HD 7790 wins on price. Its launch MSRP of 149 USD is substantially lower than the RTX 3060 Ti's 399 USD. For a budget-oriented legacy build, the HD 7790 costs far less upfront.

NVIDIA GeForce RTX 3060 Ti wins on compute performance. Its shading unit count (4,864 versus 896), FP32 throughput (16.20 TFLOPS versus 1.792 TFLOPS), texture rate (253.1 GTexel/s versus 56.00 GTexel/s), and pixel rate (133.2 GPixel/s versus 16.00 GPixel/s) all favor the NVIDIA card by wide margins.

NVIDIA GeForce RTX 3060 Ti wins on memory. 8 GB of GDDR6 on a 256-bit bus with 448.0 GB/s bandwidth is a massive upgrade over 1 GB of GDDR5 on a 128-bit bus with 96.00 GB/s. This makes the RTX card viable for high-resolution textures, large datasets, and modern games.

NVIDIA GeForce RTX 3060 Ti wins on feature set. RT cores, tensor cores, DirectX 12 Ultimate, and Vulkan 1.4 support give it capabilities the HD 7790 simply cannot match. The PCIe 4.0 interface and HDMI 2.1 output also keep it relevant with current hardware.

NVIDIA GeForce RTX 3060 Ti wins on raw benchmark breadth. It has recorded scores across multiple test suites including 3DMark Steel Nomad DX12 (2,626), Geekbench OpenCL (78,927), Geekbench Vulkan (47,784), and PassMark G3D (20,349). The HD 7790 has only a Geekbench Metal score of 17,666, which limits its comparability.

For a modern gaming or productivity system, the RTX 3060 Ti is the only serious option. For a period-correct retro build, low-power HTPC, or a system where the 85 W TDP and 183 mm length are critical constraints, the HD 7790 remains serviceable. The choice ultimately comes down to whether the workload demands modern features and memory capacity, or whether power and size constraints dominate.