AMD Radeon HD 7790 vs NVIDIA GeForce RTX 2060 Comparison

Head-to-Head Benchmarks

The database shows no direct head-to-head benchmark runs between the AMD Radeon HD 7790 and the NVIDIA GeForce RTX 2060. Instead, the comparison relies on their respective average benchmark scores and the nearest rival entries that bracket each card.

The AMD Radeon HD 7790 posts an average benchmark score of 17,666, placing it at the 61st percentile of all GPUs in the database. That score comes from a single Geekbench Metal test, which is the only recorded benchmark for this card. The NVIDIA GeForce RTX 2060, by contrast, has a much richer benchmark profile, with ten recorded tests spanning DirectX 9 through DirectX 12, OpenCL, Vulkan, and compute workloads. Its average benchmark score is 15,290, which sits at the 58th percentile.

The raw averages tell a surprising story: the HD 7790, a card from 2013, actually edges out the RTX 2060 in average score by roughly 2,376 points, or about 15.5%. That gap is driven by the HD 7790's strong showing in the Geekbench Metal test, which is a macOS-centric workload. The RTX 2060's average is dragged down by its Passmark DirectX 9 score of 190, its Passmark DirectX 10 score of 98, and its Passmark DirectX 11 score of 110, all of which are low compared to its other results.

Looking at the nearest rivals for each card clarifies the picture. The HD 7790's closest competitor is the NVIDIA GeForce RTX 4060, which scores 17,639, a delta of just 0.2% behind the HD 7790. The AMD Radeon 780M sits 0.4% behind at 17,588, and the AMD Radeon Pro 560 trails by 0.7% at 17,551. The NVIDIA Quadro RTX 4000 leads the HD 7790 by 0.7% with a score of 17,789. These are all modern or near-modern parts, which suggests the HD 7790's Metal score is anomalously high for its era.

For the RTX 2060, the nearest rivals cluster tightly around its 15,290 average. The NVIDIA GeForce GTX 580 matches it exactly at 15,283, a 0% delta. The AMD Radeon 680M trails by 0.1% at 15,270, the NVIDIA GeForce RTX 3050 OEM trails by 0.6% at 15,199, and the AMD Radeon RX 7600 trails by 0.8% at 15,171. Notably, the RTX 2060's nearest rivals are all much newer or much older parts, indicating that its performance profile is something of a mid-pack outlier.

The RTX 2060's individual scores reveal its strengths and weaknesses. Its best result is in Geekbench Vulkan at 65,846, followed closely by Geekbench OpenCL at 65,014. Its Passmark G3D score is 14,111, and its compute score is 5,488. The DirectX-specific Passmark scores are far lower: 53 for DirectX 12, 98 for DirectX 10, 110 for DirectX 11, and 190 for DirectX 9. The G2D score is 745. These numbers suggest the RTX 2060 is strongest in general-purpose compute and Vulkan workloads, while its DirectX performance is comparatively modest.

The HD 7790's single Metal score of 17,666 is harder to contextualize without more data points. It is possible that the Metal test favors certain architectural traits, or that the test's scaling behavior inflates scores for older GCN parts relative to newer Turing cards. The fact that the HD 7790's nearest rivals are all cards with similar Metal scores, despite being from different generations, points to a test-specific clustering effect rather than a general performance parity.

The Verdict

The data presents a paradox. By average benchmark score, the AMD Radeon HD 7790 appears to outperform the NVIDIA GeForce RTX 2060, with 17,666 versus 15,290. However, that conclusion is fragile because it rests on a single benchmark for the HD 7790 versus ten benchmarks for the RTX 2060. The HD 7790's percentile ranking of 61st is also higher than the RTX 2060's 58th, reinforcing the score-based view.

Yet the RTX 2060 has clear architectural advantages that the benchmark averages do not capture. It has 1,920 shading units versus 896, 120 texture mapping units versus 56, and 48 render output units versus 16. Its memory configuration is substantially larger: 6 GB of GDDR6 on a 192-bit bus with 336.0 GB/s bandwidth, compared to 1 GB of GDDR5 on a 128-bit bus with 96.00 GB/s bandwidth. The RTX 2060 also carries 30 ray tracing cores and 240 tensor cores, features the HD 7790 lacks entirely.

The RTX 2060's pixel rate is 80.64 GPixel/s versus 16.00 GPixel/s for the HD 7790, and its texture rate is 201.6 GTexel/s versus 56.00 GTexel/s. Its FP32 throughput is 6.451 TFLOPS versus 1.792 TFLOPS. These figures indicate that, for traditional rasterization workloads, the RTX 2060 should be vastly faster. The Passmark G3D score of 14,111 for the RTX 2060, while not directly comparable to the HD 7790's Metal score, is the more conventional gaming metric and suggests strong DirectX performance.

Who should pick which depends entirely on the workload. If the priority is a specific Metal-based benchmark score, the HD 7790 wins. If the priority is modern API support, memory capacity, ray tracing, tensor operations, or raw throughput, the RTX 2060 wins decisively. The database also shows the RTX 2060 supports DirectX 12 Ultimate (12_2) and Vulkan 1.4, while the HD 7790 tops out at DirectX 12 (12_0) and Vulkan 1.2.170.

FAQ

Q: Which card has the higher average benchmark score?

A: The AMD Radeon HD 7790 has an average benchmark score of 17,666, while the NVIDIA GeForce RTX 2060 has an average of 15,290.

Q: How many benchmarks does each card have recorded?

A: The HD 7790 has one recorded benchmark (Geekbench Metal), while the RTX 2060 has ten recorded benchmarks spanning DirectX, OpenCL, Vulkan, and compute tests.

Q: What is the closest rival to the HD 7790?

A: The NVIDIA GeForce RTX 4060 is the closest rival with an average score of 17,639, a delta of 0.2% behind the HD 7790.

Q: What is the closest rival to the RTX 2060?

A: The NVIDIA GeForce GTX 580 is the closest rival with an average score of 15,283, a delta of 0% relative to the RTX 2060.

Q: Does the RTX 2060 support ray tracing cores?

A: Yes, the RTX 2060 has 30 ray tracing cores and 240 tensor cores, while the HD 7790 has none.

Q: Which card has higher memory bandwidth?

A: The RTX 2060 has 336.0 GB/s bandwidth on a 192-bit bus with 6 GB of GDDR6, while the HD 7790 has 96.00 GB/s on a 128-bit bus with 1 GB of GDDR5.

Specification Differences

The two cards differ across nearly every specification field. The HD 7790 uses a 28 nm process node, while the RTX 2060 uses 12 nm. The HD 7790's chip is Bonaire with GCN 2.0 architecture, while the RTX 2060 uses TU106 with Turing architecture. Transistor counts differ greatly: 2,080 million for the HD 7790 versus 10,800 million for the RTX 2060. Die size is 160 mm² for the HD 7790 and 445 mm² for the RTX 2060. Transistor density is 13.0M per mm² versus 24.3M per mm².

Clock speeds are only listed for the RTX 2060, with a base of 1365 MHz and boost of 1680 MHz. Memory clocks show 1500 MHz (6 Gbps effective) for the HD 7790 and 1750 MHz (14 Gbps effective) for the RTX 2060. Memory size is 1024 MB versus 6 GB, memory type is GDDR5 versus GDDR6, bus width is 128 bit versus 192 bit, and bandwidth is 96.00 GB/s versus 336.0 GB/s.

Shading units are 896 versus 1920, TMUs are 56 versus 120, and ROPs are 16 versus 48. The RTX 2060 adds 30 RT cores and 240 tensor cores. Pixel rate is 16.00 GPixel/s versus 80.64 GPixel/s, texture rate is 56.00 GTexel/s versus 201.6 GTexel/s, and FP32 is 1.792 TFLOPS versus 6.451 TFLOPS. The RTX 2060 also lists FP16 at 12.90 TFLOPS (2:1), which the HD 7790 does not.

TDP is 85 W for the HD 7790 and 160 W for the RTX 2060. Power connectors are 1x 6-pin versus 1x 8-pin, and suggested PSU is 250 W versus 450 W. Display outputs differ: the HD 7790 has 1x DVI, 1x HDMI 1.4a, and 2x mini-DisplayPort 1.2, while the RTX 2060 has 1x DVI, 1x HDMI 2.0, 2x DisplayPort 1.4a, and 1x USB Type-C. Dimensions differ as well: 183 mm (7.2 inches) length for the HD 7790, versus 229 mm (9 inches) length, 113 mm (4.4 inches) height, and 35 mm (1.4 inches) width for the RTX 2060.

Architecture Differences

The HD 7790 is built on GCN 2.0, part of the Southern Islands generation (HD 7700 family), using the Bonaire chip. The RTX 2060 uses the Turing architecture with the TU106 chip, part of the GeForce 20 series. The process node difference is significant: 28 nm for the HD 7790 versus 12 nm for the RTX 2060, both fabbed by TSMC. The RTX 2060 packs over five times the transistors (10,800 million versus 2,080 million) into a die nearly three times larger (445 mm² versus 160 mm²).

Memory architecture diverges completely. The HD 7790 uses 1 GB of GDDR5 on a 128-bit bus, while the RTX 2060 uses 6 GB of GDDR6 on a 192-bit bus. The bandwidth gap is 3.5 times in favor of the RTX 2060 (336.0 GB/s versus 96.00 GB/s). The RTX 2060's memory clock is 1750 MHz (14 Gbps effective) versus 1500 MHz (6 Gbps effective) for the HD 7790.

The RTX 2060 introduces dedicated hardware absent from the HD 7790: 30 ray tracing cores and 240 tensor cores. These enable hardware-accelerated ray tracing and AI-based tensor operations, features that did not exist in GCN 2.0. The HD 7790 has no equivalent units. API support also differs: the RTX 2060 supports DirectX 12 Ultimate (12_2) and Vulkan 1.4, while the HD 7790 supports DirectX 12 (12_0) and Vulkan 1.2.170. Both support OpenGL 4.6.

The HD 7790 uses a 1x 6-pin power connector with an 85 W TDP and 250 W suggested PSU. The RTX 2060 uses a 1x 8-pin connector with a 160 W TDP and 450 W suggested PSU. Both are dual-slot cards, and both use PCIe 3.0 x16 interfaces. The HD 7790's display outputs are older-generation (HDMI 1.4a, mini-DisplayPort 1.2), while the RTX 2060 supports HDMI 2.0, DisplayPort 1.4a, and adds a USB Type-C output.

Where Each One Wins

The HD 7790 wins in the Geekbench Metal benchmark, scoring 17,666, which is its only recorded test. This single result places it above the RTX 2060's average and gives it a higher percentile ranking (61st versus 58th). The HD 7790 also wins on power efficiency in terms of TDP, drawing 85 W versus 160 W, and it requires a less substantial PSU (250 W versus 450 W). Its physical footprint is smaller at 183 mm length versus 229 mm.

The RTX 2060 wins across nearly every other measurable category. In raw throughput, it delivers 6.451 TFLOPS FP32 versus 1.792 TFLOPS, a 3.6 times advantage. Its pixel rate of 80.64 GPixel/s is 5 times the HD 7790's 16.00 GPixel/s, and its texture rate of 201.6 GTexel/s is 3.6 times the HD 7790's 56.00 GTexel/s. Memory bandwidth is 3.5 times higher, and memory capacity is 6 times larger.

The RTX 2060 wins in API compatibility, offering DirectX 12 Ultimate (12_2) and Vulkan 1.4, versus DirectX 12 (12_0) and Vulkan 1.2.170 for the HD 7790. It is the only card of the two with ray tracing cores and tensor cores. In the recorded benchmark suite, the RTX 2060 shows strong Vulkan performance with a Geekbench Vulkan score of 65,846 and OpenCL score of 65,014, though these tests were not run on the HD 7790. The RTX 2060's Passmark G3D score of 14,111 provides a conventional DirectX gaming metric, while no comparable G3D score exists for the HD 7790.

For gamers and compute users, the RTX 2060 is the clear choice based on architecture, memory, and feature support. For someone specifically optimizing for the Metal benchmark workload, the HD 7790's recorded score is higher, but that is a narrow and possibly misleading slice of its overall capability. The data supports the RTX 2060 as the more capable card for modern workloads, with the HD 7790's lone benchmark win being an outlier rather than a trend.