NVIDIA GeForce RTX 2060 Mobile

NVIDIA’s RTX 2060 Mobile is a 12 nm Turing-based part for laptops, built around the TU106 chip with 10,800 million transistors on a 445 mm² die. It holds the 50th percentile among all GPUs in the database, placing it squarely in the middle of the pack. The data shows a balanced configuration: 1,920 shading units, 120 TMUs, and 48 ROPs, paired with 6 GB of GDDR6 memory on a 192-bit bus. Its memory clock runs at 1750 MHz, yielding 14 Gbps effective speed and a bandwidth of 336.0 GB/s. The GPU’s base clock is 960 MHz, boosting to 1200 MHz, which translates to a peak FP32 throughput of 4.608 TFLOPS. Pixel fill rate is 57.60 GPixel/s, and texture rate is 144.0 GTexel/s. This is a mid-range mobile part from the GeForce 20-series, positioned between the preceding GeForce 10 Mobile and the subsequent GeForce 30 Mobile.

Benchmark Performance

The RTX 2060 Mobile’s performance profile is defined by its 50th percentile ranking across all GPUs, indicating that roughly half of the database entries are faster and half are slower. This places it as a solid mainstream option, but not a high-end performer. With an average benchmark score of 0 in the current dataset, there are no direct numerical comparisons to other cards; however, the percentile figure is the key differentiator here. A 50th percentile result suggests that in typical gaming workloads, this GPU will handle 1080p and some 1440p titles at medium-to-high settings, though it will struggle with demanding titles at maximum presets.

The FP32 compute of 4.608 TFLOPS is a raw measure of shader throughput. This number, combined with the 144.0 GTexel/s texture rate, indicates that the card can process geometry and textures at a rate consistent with its mid-range classification. The 57.60 GPixel/s pixel rate further supports this, suggesting that fill-rate-bound scenarios at high resolutions will be a limiting factor. In multi-core or multi-threaded workloads that leverage the Tensor cores, the FP16 performance of 9.216 TFLOPS (2:1) doubles the raw throughput, which can be beneficial for AI-accelerated features like DLSS, though the absence of benchmark scores prevents a direct percentage comparison to rivals.

The memory subsystem is a notable strength. The 336.0 GB/s bandwidth is ample for the 6 GB frame buffer, ensuring that texture streaming and high-resolution assets do not become a bottleneck in most scenarios. The 192-bit bus width is a standard configuration for this class, and the 14 Gbps effective memory speed is competitive for the era. Data indicates that the card’s overall performance is balanced, with no single subsystem dramatically outperforming the others, which is typical for a Turing-based mid-range mobile GPU.

How It Compares

Since the nearestRivals array is empty in the FACT PACK, direct comparisons to specific competitor models cannot be quantified with percentages. However, the data positions the RTX 2060 Mobile within its own generation and lineage. As a successor to the GeForce 10 Mobile series, it introduces Turing-specific features like dedicated ray tracing and tensor cores, which were absent in the predecessor. The performance uplift over the older architecture is qualitative, but the architectural advancements—namely the additional processing units for RT and AI—provide a feature-based advantage that raw rasterization scores may not fully capture.

Relative to its successor, the GeForce 30 Mobile, the RTX 2060 Mobile is a step down in both performance and efficiency. The 12 nm process node, while mature, is less dense than the newer manufacturing technologies used in the 30-series. The 50th percentile ranking means that in a mixed pool of GPUs, it will be outperformed by the higher-tier 30-series parts, but it also means it will outpace many entry-level and older discrete mobile GPUs. The lack of rival data means the analysis must rely on the percentile: a mid-pack placement suggests that users will experience consistent 60 FPS gameplay in esports titles and older AAA games, but will need to lower settings for the latest releases.

Without specific rival scores, the comparison is structural. The 30 RT cores and 240 Tensor cores are the defining features, setting it apart from non-RT cards. In workloads that use DirectX 12 Ultimate (12_2), the RTX 2060 Mobile supports the full feature set, including variable rate shading and mesh shaders, which are also present in newer cards. This ensures a level of future-proofing for API-level features, even if raw performance is not top-tier.

Ray Tracing and Feature Set

The RTX 2060 Mobile includes 30 RT cores and 240 Tensor cores, which are the dedicated hardware units for ray tracing and AI processing, respectively. This is a foundational feature of the Turing architecture, bringing real-time ray-traced lighting and shadows to laptops. The RT core count, while lower than desktop counterparts, is sufficient for enabling ray-traced effects at playable frame rates when combined with DLSS, which leverages the Tensor cores to upscale resolutions. The Tensor cores provide a 2:1 FP16 rate, delivering 9.216 TFLOPS for AI workloads, which is double the FP32 throughput.

In terms of API support, the card is fully compliant with DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. This ensures compatibility with the latest gaming titles and development frameworks. DirectX 12 Ultimate is a key feature, as it guarantees support for hardware-accelerated ray tracing, variable rate shading, and mesh shaders, aligning the mobile GPU with the feature set of contemporary desktop cards. The Vulkan 1.4 support also allows for cross-platform development and high-efficiency rendering paths.

The display outputs are listed as "Portable Device Dependent," meaning the actual ports (HDMI, DisplayPort, etc.) vary by laptop manufacturer. The bus interface is PCIe 3.0 x16, which is standard for the generation. The combination of RT cores, Tensor cores, and modern API support makes this GPU a capable platform for both gaming and content creation tasks that benefit from AI acceleration, such as denoising or upscaling.

FAQ

Q: What is the memory configuration of the RTX 2060 Mobile?

A: It features 6 GB of GDDR6 memory on a 192-bit bus, with a bandwidth of 336.0 GB/s and an effective speed of 14 Gbps.

Q: Does the RTX 2060 Mobile support hardware ray tracing?

A: Yes, it includes 30 dedicated RT cores, which enable real-time ray-traced effects in supported titles.

Q: What is the process node and chip size?

A: The GPU is built on a 12 nm process at TSMC, with a die size of 445 mm² and a transistor count of 10,800 million.

Q: What is the peak FP32 performance?

A: The FP32 throughput is 4.608 TFLOPS, based on a 1200 MHz boost clock and 1,920 shading units.

Q: Which APIs are supported?

A: The card supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Q: How does the FP16 performance compare to FP32?

A: FP16 performance is 9.216 TFLOPS, which is a 2:1 ratio relative to the FP32 figure, enabled by the Tensor cores.

Power and Cooling

The RTX 2060 Mobile has a TDP of 115 W, which is a typical figure for a mid-range mobile GPU of its generation. This power envelope requires a dedicated cooling solution within the laptop chassis, but it is not excessively demanding. The slot width is designated as "MXM Module," indicating that the GPU is mounted on a removable MXM board, which allows for potential upgrades or replacements in compatible laptops. The power connectors are listed as "None," meaning power is delivered directly through the MXM interface rather than external PCIe power cables.

There is no suggested PSU rating in the FACT PACK, which is common for mobile parts since the power supply is integrated into the laptop’s AC adapter and internal VRM design. The absence of external power connectors simplifies installation and reduces cable clutter. For a desktop comparison, the 115 W TDP is lower than many desktop cards, but it still generates significant heat that must be managed by the laptop’s thermal system. The end-of-life production status indicates that this GPU is no longer in active manufacturing, but its power characteristics remain relevant for users of existing systems.

The 12 nm process node, while not the most efficient by modern standards, is adequate for the 115 W power budget. The memory clock of 1750 MHz (14 Gbps effective) contributes to the overall power draw, but the balanced configuration ensures that no single component is overstressed. Since the suggested PSU is null, the data does not provide a specific wattage recommendation for a desktop equivalent; however, the mobile form factor relies on the laptop’s internal power delivery, which is designed around the 115 W TDP.