AMD Radeon RX Vega M GL vs NVIDIA GeForce RTX 2060 SUPER Comparison

The Verdict

The recorded data splits these two GPUs cleanly by workload class. The NVIDIA GeForce RTX 2060 SUPER dominates every shared benchmark, winning both head-to-head tests by wide margins. In Geekbench OpenCL, the RTX 2060 SUPER scores 76957 against 19549 for the AMD Radeon RX Vega M GL, a delta of -74.6% from the AMD part's perspective. In Geekbench Vulkan, the NVIDIA card posts 77402 versus 22757, a -70.6% gap. The RTX 2060 SUPER is the clear choice for any user whose priority is raw compute performance in these cross-platform tests.

The AMD Radeon RX Vega M GL, however, occupies a different niche entirely. Its 65 W TDP and IGP bus interface place it in integrated-class territory, while the RTX 2060 SUPER draws 175 W and requires a dual-slot cooler with a single 8-pin power connector. The data shows the AMD part is for compact, low-power systems where a discrete GPU cannot fit. The RTX 2060 SUPER is for desktop builds with a 450 W suggested PSU and room for a 229 mm card. Users needing ray tracing, tensor cores, or higher VRAM capacity have only one option in this comparison.

Architecture Differences

The two chips come from different foundries and process nodes. AMD uses GlobalFoundries' 14 nm process for the Polaris 22 chip, while NVIDIA uses TSMC's 12 nm node for TU106. The transistor counts reflect the scale gap: AMD packs 5,000 million transistors on a 208 mm² die, yielding 24.0M transistors per mm². NVIDIA fits 10,800 million transistors on a 445 mm² die, a density of 24.3M per mm². The densities are nearly identical, but NVIDIA deploys more than twice the transistor budget.

Architecturally, AMD runs GCN 4.0 with the Vega M generation, while NVIDIA uses Turing from the GeForce 20 series. The shading resources differ substantially: AMD has 1280 shading units, 80 TMUs, and 32 ROPs. NVIDIA has 2176 shading units, 136 TMUs, and 64 ROPs. The RTX 2060 SUPER also includes 34 RT cores and 272 tensor cores, which the AMD part lacks entirely. This is a fundamental feature split: the NVIDIA GPU can accelerate ray tracing and AI workloads through dedicated hardware, while the AMD GPU relies on its general-purpose shaders.

Memory architecture also diverges. AMD uses 4 GB of HBM2 on a 1024-bit bus, delivering 179.2 GB/s bandwidth at a 700 MHz memory clock (1400 Mbps effective). NVIDIA uses 8 GB of GDDR6 on a 256-bit bus, delivering 448.0 GB/s at 1750 MHz (14 Gbps effective). The AMD HBM2 setup offers a wider bus but lower total capacity and bandwidth. The API support differs as well: AMD lists DirectX 12 (12_0), OpenGL 4.6, and Vulkan 1.3. NVIDIA lists DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, the newer specification for both DirectX and Vulkan.

Head-to-Head Benchmarks

The shared benchmark set contains only two tests, and NVIDIA wins both. In Geekbench OpenCL, the RTX 2060 SUPER scores 76957, which is 57408 points higher than the RX Vega M GL's 19549. The percentage delta of -74.6% means the AMD part achieves roughly a quarter of the NVIDIA score. This is not a close contest; the NVIDIA card delivers nearly four times the OpenCL compute result.

Geekbench Vulkan tells the same story with a slightly smaller gap. The RTX 2060 SUPER posts 77402, while the RX Vega M GL reaches 22757. The delta is -70.6%, so the AMD GPU again lands at roughly 29% of the NVIDIA score. The Vulkan gap is narrower than OpenCL, but still decisive.

The database also records standalone benchmark averages. The RX Vega M GL has an average benchmark score of 21153 across its two tests, with a percentile rank of 66 among all GPUs. The RTX 2060 SUPER has an average of 18093 across ten tests, with a percentile rank of 62. These averages are not directly comparable because the test sets differ, but they show the AMD part's limited test coverage versus the NVIDIA card's broader validation suite. The NVIDIA card's individual results include Passmark G3D at 16462, Passmark GPU Compute at 6721, and a 3DMark Steel Nomad DX12 score of 2011.

Specification Differences

The two GPUs differ in nearly every measurable specification. The process node: 14 nm for AMD, 12 nm for NVIDIA. The foundry: GlobalFoundries versus TSMC. Transistors: 5,000 million versus 10,800 million. Die size: 208 mm² versus 445 mm². Transistor density is close, 24.0M versus 24.3M per mm², but the raw scale favors NVIDIA.

Clock speeds favor NVIDIA as well. AMD runs at 931 MHz base and 1011 MHz boost. NVIDIA runs at 1470 MHz base and 1650 MHz boost. Memory clocks: AMD at 700 MHz (1400 Mbps effective), NVIDIA at 1750 MHz (14 Gbps effective). Memory capacity: 4 GB HBM2 versus 8 GB GDDR6. Bus width: 1024-bit versus 256-bit. Bandwidth: 179.2 GB/s versus 448.0 GB/s.

Compute resources: 1280 shading units, 80 TMUs, 32 ROPs, no RT cores, no tensor cores for AMD. NVIDIA has 2176 shading units, 136 TMUs, 64 ROPs, 34 RT cores, 272 tensor cores. Pixel rate: 32.35 GPixel/s versus 105.6 GPixel/s. Texture rate: 80.88 GTexel/s versus 224.4 GTexel/s. FP32: 2.588 TFLOPS versus 7.181 TFLOPS. FP16: AMD at 2.588 TFLOPS with a 1:1 ratio, NVIDIA at 14.36 TFLOPS with a 2:1 ratio.

Power and physical specifications diverge sharply. AMD has a 65 W TDP, IGP slot width, no power connectors, no suggested PSU, and an IGP bus interface. NVIDIA has a 175 W TDP, dual-slot width, one 8-pin power connector, a 450 W suggested PSU, and PCIe 3.0 x16. Dimensions: the AMD part has no recorded length, height, or width, as it is an integrated product. The NVIDIA card measures 229 mm long, 113 mm high, and 35 mm wide. Display outputs: AMD lists "Portable Device Dependent," while NVIDIA offers 1x DVI, 1x HDMI 2.0, 2x DisplayPort 1.4a, and 1x USB Type-C. Production status for both is end-of-life. Release dates: AMD on 2018-01-31, NVIDIA on 2019-07-08. The NVIDIA part has a launch MSRP of 399 USD.

FAQ

Q: Which GPU has higher raw compute performance in shared benchmarks?

A: The NVIDIA GeForce RTX 2060 SUPER wins both shared tests. It scores 76957 in Geekbench OpenCL versus 19549 for the AMD Radeon RX Vega M GL, and 77402 in Geekbench Vulkan versus 22757, for deltas of -74.6% and -70.6% respectively.

Q: Does the AMD Radeon RX Vega M GL support ray tracing or tensor operations?

A: No. The AMD part has no RT cores and no tensor cores in its specification. The NVIDIA GeForce RTX 2060 SUPER includes 34 RT cores and 272 tensor cores.

Q: How do memory capacities compare between the two GPUs?

A: The AMD Radeon RX Vega M GL has 4 GB of HBM2 on a 1024-bit bus with 179.2 GB/s bandwidth. The NVIDIA GeForce RTX 2060 SUPER has 8 GB of GDDR6 on a 256-bit bus with 448.0 GB/s bandwidth.

Q: Which GPU is suitable for a compact or low-power system?

A: The AMD Radeon RX Vega M GL, with a 65 W TDP, IGP slot width, and no power connectors, is designed for integrated use in portable devices and compact platforms. The NVIDIA card requires a dual-slot cooler, a 1x 8-pin power connector, and a 450 W suggested PSU.

Q: What are the API differences between the two?

A: The AMD Radeon RX Vega M GL supports DirectX 12 (12_0), OpenGL 4.6, and Vulkan 1.3. The NVIDIA GeForce RTX 2060 SUPER supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Q: What is the release timeline for each GPU?

A: The AMD Radeon RX Vega M GL was released on 2018-01-31. The NVIDIA GeForce RTX 2060 SUPER was released on 2019-07-08. Both are now end-of-life products.

Where Each One Wins

The NVIDIA GeForce RTX 2060 SUPER wins in every measured performance category. Its FP32 throughput of 7.181 TFLOPS is nearly three times the AMD part's 2.588 TFLOPS. Pixel rate of 105.6 GPixel/s versus 32.35 GPixel/s gives it a strong edge in fill-rate-bound scenes. Texture rate of 224.4 GTexel/s versus 80.88 GTexel/s doubles down on that advantage. The 448.0 GB/s memory bandwidth versus 179.2 GB/s matters for high-resolution textures and large data sets. The 8 GB VRAM capacity versus 4 GB allows larger assets to stay resident. The 34 RT cores and 272 tensor cores open up ray-traced effects and AI-accelerated features that the AMD GPU cannot execute in hardware.

The AMD Radeon RX Vega M GL wins on integration and power envelope. Its 65 W TDP is less than half the NVIDIA card's 175 W. It requires no power connectors, no suggested PSU, and no expansion slot beyond its IGP interface. Its 208 mm² die is smaller than the 445 mm² NVIDIA die, and its 5,000 million transistors versus 10,800 million reflect a much lighter silicon budget. The 1024-bit HBM2 bus provides a wide memory path, even if the total bandwidth is lower. For a system designer constrained by thermal limits or physical space, the AMD part fits where the NVIDIA card cannot.

The use-case split is therefore clean. The RTX 2060 SUPER serves desktop users who need maximum compute, ray tracing, tensor performance, and 8 GB of VRAM, and who can supply a 450 W PSU and dual-slot clearance. The RX Vega M GL serves integrated or portable platforms where the 65 W TDP and IGP form factor are the deciding factors, and where the performance gap in the recorded benchmarks is an acceptable trade-off. The data does not present these as direct competitors; it presents them as solutions to different hardware constraints.