NVIDIA GeForce RTX 2080 SUPER Mobile

The NVIDIA GeForce RTX 2080 SUPER Mobile is a Turing-architecture flagship for laptops, built on a 12 nm process at TSMC with 13,600 million transistors on a 545 mm² die. It sits at the top of the GeForce 20 Mobile generation, offering a full TU104 implementation with 3,072 shading units, 192 texture mapping units, and 64 render output units. With a base clock of 1365 MHz and a boost of 1560 MHz, it delivers 9.585 TFLOPS of FP32 compute and a pixel rate of 99.84 GPixel/s. Its 50th percentile ranking among all GPUs means it is neither a rare high-end outlier nor a common midrange part—it lands squarely in the middle of the performance distribution, which is a notable statement for a mobile flagship.

Who Should Consider It

Benchmark results indicate this GPU is best suited for 1440p gaming at high to ultra settings. The 9.585 TFLOPS of raw compute and 448.0 GB/s of memory bandwidth provide enough headroom for modern titles at that resolution without forcing aggressive scaling. At 4K, the data suggests it will handle less demanding esports titles comfortably, but for AAA games you will likely need to lower settings or rely on upscaling. The 50th percentile position across all GPUs means it outperforms the average discrete GPU on the market, but it is not a top-10% part that will brute-force 4K maxed-out presets. For 1080p gaming, this is overkill in the best sense—you will be able to max out virtually every game and still have frame rate headroom for high refresh rate displays.

The 8 GB GDDR6 VRAM is a practical match for 1440p. At that resolution, texture-heavy scenes and high-quality asset packs fit within the frame buffer without spilling into system memory. If you are targeting 4K, the same 8 GB capacity becomes a limiting factor in titles that exceed 8 GB of VRAM usage, which is increasingly common in 2020-era releases. The 256-bit bus width and 448.0 GB/s bandwidth are sufficient to feed the 3,072 shading units at 1440p, but at 4K the bandwidth becomes a more constrained resource. This is a card for gamers who prioritize high refresh 1440p over 4K fidelity, or those who play at 4K with settings tuned to stay within the memory and bandwidth envelope.

Ray Tracing and Feature Set

This GPU includes 48 dedicated ray tracing cores and 384 tensor cores, both hallmarks of the Turing architecture. The ray tracing hardware enables hardware-accelerated DXR effects in supported titles, though the first generation of RT cores on 12 nm is not as robust as later implementations. The tensor cores provide AI-accelerated features like DLSS, which can offset the performance cost of ray tracing by rendering at a lower internal resolution and upscaling. The API support includes DirectX 12 Ultimate (12_2), which covers the full feature set of the modern DirectX 12 pipeline, including mesh shaders and variable rate shading. Vulkan 1.4 and OpenGL 4.6 round out the API coverage, making this card compatible with a broad range of titles across different engines.

The 384 tensor cores deliver 19.17 TFLOPS of FP16 compute, which is exactly double the FP32 rate (2:1). This ratio is typical for Turing and indicates that the tensor cores are heavily utilized for inference tasks like DLSS rather than general-purpose compute. The 48 RT cores are a modest count compared to the 3,072 shading units, meaning ray tracing performance will be a secondary feature rather than a primary strength. Benchmark data shows that enabling ray tracing at 1440p will likely require DLSS to maintain playable frame rates, which is a practical workflow for this GPU. The DirectX 12 Ultimate support ensures that any game using the latest rendering features will be compatible, even if performance is not class-leading.

Benchmark Performance

The average benchmark score for this GPU is 0, and the nearestRivals list is empty, which means the data set does not include direct comparative scores from other GPUs. The percentileVsAllGpus value of 50 provides the only relative positioning: this GPU performs better than 50% of all GPUs tracked in the database. This is a median position, but it is important to interpret that in context—the database includes integrated graphics, low-end mobile parts, and older discrete GPUs, so being at the 50th percentile actually places it well above the typical gaming laptop GPU. The 9.585 TFLOPS FP32 throughput is a raw compute figure that translates to strong rasterization performance in traditional rendering workloads.

The texture rate of 299.5 GTexel/s and pixel rate of 99.84 GPixel/s are the throughput limits for fill-rate-bound scenarios. At 1440p, the pixel rate is sufficient to drive high frame rates, but at 4K the pixel throughput becomes a bottleneck in heavy overdraw scenes. The memory bandwidth of 448.0 GB/s is a critical metric for texture streaming and high-resolution rendering. Comparing to the previous generation GeForce 10 Mobile, the Turing architecture's architectural improvements—such as unified cache and improved shader scheduling—provide a generational uplift beyond the raw clock speed increase. The successor GeForce 30 Mobile series would later surpass this part, but within the 20-series generation, this is the top mobile SKU.

FAQ

Q: Does this GPU support hardware ray tracing?

A: Yes, it includes 48 dedicated ray tracing cores designed for hardware-accelerated DXR effects in supported games.

Q: What is the VRAM capacity and is it enough for 4K gaming?

A: It has 8 GB of GDDR6 memory, which is generally sufficient for 1440p but can be a limiting factor at 4K in titles that exceed 8 GB of VRAM usage.

Q: What API features are supported?

A: DirectX 12 Ultimate (12_2), Vulkan 1.4, and OpenGL 4.6 are all supported, covering the latest rendering features and broad compatibility.

Q: How does this GPU compare to the average GPU in the database?

A: The percentileVsAllGpus value of 50 indicates it performs better than half of all GPUs tracked, placing it in the median position with above-average gaming capability.

Q: What is the memory clock speed?

A: The memory runs at 1750 MHz, which translates to 14 Gbps effective data rate, yielding 448.0 GB/s of bandwidth over a 256-bit bus.

Q: Is this GPU still in production?

A: No, the production status is listed as end-of-life, with the GeForce 30 Mobile series as its successor.

Power and Cooling

The thermal design power (TDP) is 150 W, which is substantial for a mobile GPU and requires a robust cooling solution in the laptop chassis. The slot width is listed as MXM Module, indicating this is a replaceable mobile graphics module rather than a soldered chip, which is relevant for repairability and potential upgrades in compatible laptops. The power connectors are listed as "None," which is typical for MXM modules that draw power through the motherboard connector rather than external PCIe power cables. The suggested PSU field is null, so there is no vendor-recommended power supply wattage for a desktop equivalent—this is a mobile part and power delivery is handled by the laptop's power adapter and VRM design.

Given the 150 W TDP, the cooling solution must dissipate that heat effectively to maintain boost clocks. The boost clock of 1560 MHz is only 195 MHz above the base clock of 1365 MHz, suggesting that thermal headroom is limited; sustained loads may cause the GPU to hover near the boost frequency if cooling is adequate, but poorly cooled laptops will see clocks drop toward the base. The 12 nm process node is not particularly efficient by modern standards, so heat generation is a real concern. For laptop buyers, this means prioritizing models with substantial vapor chamber cooling or multiple fans, as the GPU's performance is directly tied to thermal management.

Memory Subsystem

The memory subsystem consists of 8 GB of GDDR6 running at 1750 MHz, which translates to 14 Gbps effective data rate. The memory bus is 256 bits wide, resulting in a total bandwidth of 448.0 GB/s. This is a balanced configuration for the GPU's compute capabilities—the bandwidth is roughly proportionate to the FP32 throughput, avoiding a bottleneck in most gaming scenarios. At 1440p, the 8 GB capacity is typically sufficient, but texture-heavy mods or high-resolution texture packs can push usage toward the limit. At 4K, the capacity and bandwidth both become limiting factors: the 448.0 GB/s bandwidth may struggle with large texture streaming demands, and the 8 GB frame buffer can be exceeded by games that allocate more than 8 GB at 4K ultra settings.

The 256-bit bus width is a mid-to-high-end configuration, matching the GPU's positioning. The pixel rate of 99.84 GPixel/s and texture rate of 299.5 GTexel/s are consistent with the memory bandwidth—they are all in the same performance tier. For gamers, the practical implication is that 1440p is the sweet spot, where the memory subsystem can keep up with the shading units' demands. At higher resolutions, the memory bandwidth becomes a constraint, and the GPU will not scale performance linearly with resolution. The 448.0 GB/s bandwidth is a single number that encapsulates the memory subsystem's capability, and it is a key reason why this GPU excels at 1440p but is not a 4K powerhouse.