NVIDIA GeForce GTX 765M vs NVIDIA GeForce RTX 3080 12 GB Comparison

Where Each One Wins

The benchmark data splits these two NVIDIA parts into completely different performance tiers, and the recorded results make the separation stark. The GeForce GTX 765M, a Kepler mobile part, shows a balanced profile across compute APIs. Its highest recorded score comes from Geekbench OpenCL at 7,176 points, with Geekbench Vulkan close behind at 6,714 and Geekbench Metal trailing at 2,612. This pattern suggests the GTX 765M handles general compute workloads reasonably well for its era, with OpenCL and Vulkan showing near parity.

The GeForce RTX 3080 12 GB, by contrast, has only one recorded benchmark in the database: 3DMark Steel Nomad DX12 at 4,791 points. That single score represents a modern DirectX 12 workload, which is a fundamentally different test from the Geekbench compute tests. The RTX 3080 12 GB wins decisively in raw modern gaming performance, as its 3DMark result targets current-generation rendering pipelines. However, the GTX 765M wins in the compute benchmark arena because it has three recorded scores across different APIs, whereas the RTX 3080 12 GB has only the one DirectX 12 test.

The use-case split is clear: the GTX 765M demonstrates strength in legacy compute scenarios where OpenCL and Vulkan workloads are present, while the RTX 3080 12 GB dominates in DirectX 12 gaming workloads. The average benchmark score tells a similar story. The GTX 765M averages 5,501 points across its three tests, while the RTX 3080 12 GB averages 4,791 from its single test. This does not mean the GTX 765M is faster overall; it means the test suites measure different things. The GTX 765M's higher average is a function of multiple compute tests, while the RTX 3080 12 GB's single gaming test is far more demanding on modern hardware.

Percentile rankings add context. The GTX 765M sits at the 32nd percentile of all GPUs, while the RTX 3080 12 GB sits at the 28th percentile. These figures come from different benchmark pools, so they are not directly comparable. The nearest rivals for each card confirm the gap. The GTX 765M trades blows with the NVIDIA GeForce MX130 (0.1% behind), AMD Radeon R7 M440 (0.3% ahead), NVIDIA Quadro M4000 (0.6% ahead), and AMD FirePro M4000 (0.7% behind). The RTX 3080 12 GB sits near the AMD Radeon R5 M255 (0.1% ahead), AMD Radeon R5 M335 (0.8% ahead), NVIDIA GeForce 940MX (1.1% behind), and NVIDIA GeForce GTX 560M (1.3% behind). These rival clusters show that each card competes in its own league, with the RTX 3080 12 GB's rivals being much older or lower-tier parts.

Architecture Differences

The architectural gap between these two GPUs spans nearly a decade of NVIDIA design philosophy. The GTX 765M uses the GK106 chip built on the Kepler architecture, fabricated by TSMC on a 28 nm process. It packs 2,540 million transistors into a 221 mm² die, yielding a transistor density of 11.5 million transistors per square millimeter. The RTX 3080 12 GB uses the GA102 chip on the Ampere architecture, fabricated by Samsung on an 8 nm process. It contains 28,300 million transistors across a 628 mm² die, with a density of 45.1 million transistors per square millimeter. That is more than an order of magnitude more transistors, and the density increase is roughly fourfold.

The memory subsystems are equally divergent. The GTX 765M comes with 2 GB of GDDR5 on a 128-bit bus, delivering 64.13 GB/s of bandwidth. The RTX 3080 12 GB features 12 GB of GDDR6X on a 384-bit bus, delivering 912.4 GB/s. The RTX 3080 12 GB has 14.2 times the memory bandwidth, which directly fuels its ability to handle high-resolution textures and modern rendering techniques.

Compute resources tell a similar story. The GTX 765M has 768 shading units, 64 texture mapping units, and 16 ROPs. The RTX 3080 12 GB has 8,960 shading units, 280 TMUs, and 96 ROPs. The RTX 3080 12 GB also adds 70 ray tracing cores and 280 tensor cores, features absent from the Kepler architecture entirely. Pixel rate jumps from 13.81 GPixel/s on the GTX 765M to 164.2 GPixel/s on the RTX 3080 12 GB, a 11.9 times increase. Texture rate jumps from 55.23 GTexel/s to 478.8 GTexel/s, an 8.7 times increase. FP32 compute leaps from 1,325.6 GFLOPS to 30.64 TFLOPS, a 23.1 times increase. The RTX 3080 12 GB also offers FP16 at 30.64 TFLOPS with a 1:1 ratio, while the GTX 765M has no recorded FP16 capability.

Clock speeds differ substantially. The GTX 765M runs at a base clock of 797 MHz and boosts to 863 MHz. The RTX 3080 12 GB runs at 1,260 MHz base and boosts to 1,710 MHz. Memory clocks are even more divergent: the GTX 765M runs at 1,002 MHz with 4 Gbps effective, while the RTX 3080 12 GB runs at 1,188 MHz with 19 Gbps effective. Power draw reflects the performance gap: the GTX 765M draws 75 W, while the RTX 3080 12 GB draws 350 W and requires a 750 W suggested power supply.

The API support also differs. The GTX 765M supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175. The RTX 3080 12 GB supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The DirectX feature level difference (11_0 vs 12_2) is significant for modern games that rely on advanced features like mesh shaders and variable rate shading. The Vulkan version is also newer on the RTX 3080 12 GB.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The GeForce GTX 765M has a higher average benchmark score at 5,501 points, compared to the GeForce RTX 3080 12 GB at 4,791 points. However, this is because the GTX 765M has three recorded Geekbench compute tests, while the RTX 3080 12 GB has a single 3DMark Steel Nomad DX12 test.

Q: What is the memory bandwidth difference between the two cards?

A: The GeForce GTX 765M delivers 64.13 GB/s of bandwidth through 2 GB of GDDR5 on a 128-bit bus. The GeForce RTX 3080 12 GB delivers 912.4 GB/s through 12 GB of GDDR6X on a 384-bit bus, which is approximately 14.2 times higher.

Q: Does the RTX 3080 12 GB support ray tracing?

A: Yes, the GeForce RTX 3080 12 GB includes 70 ray tracing cores and 280 tensor cores as part of its Ampere architecture. The GeForce GTX 765M has no ray tracing or tensor cores, as its Kepler architecture predates those features.

Q: What is the process node difference?

A: The GeForce GTX 765M is built on a 28 nm process at TSMC, while the GeForce RTX 3080 12 GB is built on an 8 nm process at Samsung. The newer process allows for 28,300 million transistors on the RTX 3080 12 GB versus 2,540 million on the GTX 765M.

Q: Which GPU has better DirectX support?

A: The GeForce RTX 3080 12 GB supports DirectX 12 Ultimate (12_2), while the GeForce GTX 765M supports DirectX 12 (11_0). The 12_2 feature level enables modern rendering features that the older Kepler part cannot handle.

Q: What are the power requirements for each card?

A: The GeForce GTX 765M has a 75 W TDP and uses no power connectors, making it suitable for MXM modules in laptops. The GeForce RTX 3080 12 GB has a 350 W TDP, requires a 1x 12-pin power connector, and needs a 750 W suggested power supply.

Specification Differences

The two GPUs differ across every major specification category. The GTX 765M belongs to the GeForce 700M generation with a release date of May 29, 2013, while the RTX 3080 12 GB belongs to the GeForce 30-series with a release date of January 10, 2022. The GTX 765M's predecessor is the GeForce 600M and its successor is the GeForce 800M. The RTX 3080 12 GB's predecessor is the GeForce 20 and its successor is the GeForce 40.

The process node shifts from 28 nm to 8 nm, and the foundry changes from TSMC to Samsung. Transistor count increases from 2,540 million to 28,300 million, die size from 221 mm² to 628 mm², and transistor density from 11.5 million per mm² to 45.1 million per mm². Clock speeds rise from 797 MHz base and 863 MHz boost to 1,260 MHz base and 1,710 MHz boost. Memory clock rises from 1,002 MHz (4 Gbps effective) to 1,188 MHz (19 Gbps effective).

Memory configuration changes from 2 GB GDDR5 on a 128-bit bus to 12 GB GDDR6X on a 384-bit bus, with bandwidth jumping from 64.13 GB/s to 912.4 GB/s. Shading units increase from 768 to 8,960, TMUs from 64 to 280, and ROPs from 16 to 96. The RTX 3080 12 GB adds 70 ray tracing cores and 280 tensor cores. Pixel rate jumps from 13.81 GPixel/s to 164.2 GPixel/s, texture rate from 55.23 GTexel/s to 478.8 GTexel/s, and FP32 from 1,325.6 GFLOPS to 30.64 TFLOPS. The RTX 3080 12 GB also has FP16 at 30.64 TFLOPS. TDP rises from 75 W to 350 W, slot width from MXM Module to Dual-slot, and power connectors from None to 1x 12-pin. The suggested PSU is 750 W for the RTX 3080 12 GB. The bus interface changes from MXM-B (3.0) to PCIe 4.0 x16. Display outputs change from Portable Device Dependent to 1x HDMI 2.1 and 3x DisplayPort 1.4a. The RTX 3080 12 GB has dimensions of 285 mm length, 112 mm height, and 40 mm width.

Head-to-Head Benchmarks

The database contains no direct head-to-head benchmark results between these two GPUs, so the comparison relies on their respective recorded scores. The GTX 765M's best result is 7,176 in Geekbench OpenCL, followed by 6,714 in Geekbench Vulkan and 2,612 in Geekbench Metal. The RTX 3080 12 GB's only result is 4,791 in 3DMark Steel Nomad DX12.

The most meaningful comparison comes from the average benchmark scores. The GTX 765M averages 5,501, which places it 14.8% ahead of the RTX 3080 12 GB's 4,791 average. But this gap is misleading because the test workloads differ. The GTX 765M's scores come from compute benchmarks that stress general-purpose GPU computation. The RTX 3080 12 GB's score comes from a modern DirectX 12 gaming benchmark that includes advanced rendering features absent from the GTX 765M's supported feature set.

In terms of rival positioning, the GTX 765M's nearest rival is the NVIDIA GeForce MX130, which scores 5,508, just 0.1% higher. The AMD Radeon R7 M440 scores 5,483, putting the GTX 765M 0.3% ahead. The NVIDIA Quadro M4000 scores 5,467, with the GTX 765M 0.6% ahead. The AMD FirePro M4000 scores 5,537, with the GTX 765M 0.7% behind. These deltas are all within 1%, indicating the GTX 765M sits in a tightly packed cluster of older mobile GPUs.

The RTX 3080 12 GB's nearest rivals are similarly close. The AMD Radeon R5 M255 scores 4,788, with the RTX 3080 12 GB 0.1% ahead. The AMD Radeon R5 M335 scores 4,752, with the RTX 3080 12 GB 0.8% ahead. The NVIDIA GeForce 940MX scores 4,844, with the RTX 3080 12 GB 1.1% behind. The NVIDIA GeForce GTX 560M scores 4,855, with the RTX 3080 12 GB 1.3% behind. All deltas stay within 1.3%, showing the RTX 3080 12 GB's recorded score places it among much older or lower-tier parts in the database's benchmark pool.

The FP32 compute difference is the largest numerical gap: 30.64 TFLOPS versus 1,325.6 GFLOPS, a 23.1 times advantage for the RTX 3080 12 GB. Memory bandwidth shows a 14.2 times advantage, and texture rate shows an 8.7 times advantage. These are the raw hardware capabilities that the single 3DMark test cannot fully capture because the GTX 765M lacks DirectX 12 Ultimate support.

The Verdict

The GeForce RTX 3080 12 GB is the overwhelmingly faster GPU for modern gaming and rendering workloads. Its 30.64 TFLOPS of FP32 compute, 912.4 GB/s of memory bandwidth, and DirectX 12 Ultimate support place it in a different hardware class than the GTX 765M. The 70 ray tracing cores and 280 tensor cores enable features the Kepler architecture cannot execute at all. The 12 GB of GDDR6X memory on a 384-bit bus provides the capacity and throughput needed for high-resolution textures and complex scenes.

The GeForce GTX 765M remains relevant only for legacy compute scenarios. Its Geekbench OpenCL score of 7,176 and Vulkan score of 6,714 show it can handle older compute workloads, and its 75 W TDP with no power connectors makes it suitable for portable devices. But its DirectX 12 (11_0) feature level, 2 GB memory capacity, and 64.13 GB/s bandwidth severely limit its modern utility.

The recorded data shows the RTX 3080 12 GB's 3DMark Steel Nomad DX12 score of 4,791 comes from a test that stresses features the GTX 765M cannot run. The GTX 765M's higher average benchmark score of 5,501 versus 4,791 stems from different test methodologies, not superior performance. The percentile rankings (32nd for the GTX 765M, 28th for the RTX 3080 12 GB) are drawn from different pools and should not be read as a direct comparison.

Who should pick which: anyone targeting modern DirectX 12 games, ray tracing, or high-resolution rendering should choose the RTX 3080 12 GB. Its launch MSRP was 799 USD. The GTX 765M is only a consideration for systems that require an MXM module with no external power connectors and run legacy OpenCL or Vulkan compute workloads. The performance gap in raw compute, memory bandwidth, and feature support is decisive in favor of the RTX 3080 12 GB for almost all use cases.