AMD Radeon HD 8750M vs NVIDIA GeForce GTX 980M Comparison

The AMD Radeon HD 8750M and NVIDIA GeForce GTX 980M occupy very different positions in the mobile graphics landscape. The recorded data shows the GTX 980M delivers a dominant performance advantage in the single shared benchmark, while the HD 8750M is an older, smaller design with far lower absolute capabilities. This analysis breaks down where each chip wins, the architectural gulf between them, and what the numbers mean for real-world use.

Where Each One Wins

The benchmark results are unambiguous: the NVIDIA GeForce GTX 980M wins the only head-to-head test recorded in the database. In Geekbench OpenCL, the GTX 980M scores 23,832 against 5,970 for the AMD Radeon HD 8750M, a difference of 74.9 percent in favor of NVIDIA. That single result means the GTX 980M claims all one recorded benchmark win, while the HD 8750M has zero wins.

However, the use-case split is not just about winning or losing. The HD 8750M is designed for lightweight, low-power mobile workloads. Its 28 nm process, 950 million transistors, and 77 mm² die size indicate a chip built for thin-and-light laptops where battery life and thermal limits take priority. The GTX 980M, by contrast, is a high-end mobile part with 5,200 million transistors on a 398 mm² die, aimed at gaming notebooks and workstation-class portable systems. The data shows the GTX 980M is in a completely different performance tier, but the HD 8750M may still be adequate for older games, basic productivity, or media playback where its lower power draw is an advantage.

The percentile rankings reinforce this split. The HD 8750M sits at the 34th percentile among all GPUs, while the GTX 980M sits at the 31st percentile. This is counterintuitive given the massive performance gap, but it reflects the database’s scoring method: the GTX 980M’s average benchmark score of 5,308 is dragged down by multiple low-scoring DirectX tests, while the HD 8750M’s single OpenCL score of 5,970 gives it a higher percentile despite far weaker absolute performance. In practice, the GTX 980M is the clear winner for anything graphics-intensive, while the HD 8750M is better suited to basic tasks where its smaller footprint and lower demands matter.

Architecture Differences

The two GPUs come from different architectural generations and design philosophies. The AMD Radeon HD 8750M uses the Mars chip built on GCN 1.0 architecture, a 28 nm design from TSMC. Its 950 million transistors are packed into a 77 mm² die, giving a transistor density of 12.3 million per square millimeter. The GTX 980M uses the GM204 chip on Maxwell 2.0 architecture, also on a 28 nm TSMC process, but with 5,200 million transistors on a much larger 398 mm² die, resulting in 13.1 million transistors per square millimeter.

Core counts differ dramatically. The HD 8750M has 384 shading units, 24 texture mapping units, and 8 render output units. The GTX 980M has 1,536 shading units, 96 TMUs, and 64 ROPs. That is exactly four times the shading units, four times the TMUs, and eight times the ROPs. These numbers directly explain the performance gap: more parallel processing units mean higher throughput in compute and graphics workloads.

Clock speeds also favor NVIDIA. The HD 8750M runs at a base clock of 775 MHz with a boost of 825 MHz. The GTX 980M operates at 1,038 MHz base and 1,127 MHz boost. Combined with the higher core counts, the GTX 980M achieves a pixel rate of 72.13 GPixel/s versus 6.600 GPixel/s for the AMD part, and a texture rate of 108.2 GTexel/s versus 19.80 GTexel/s. FP32 compute is 3.462 TFLOPS for the GTX 980M versus 633.6 GFLOPS for the HD 8750M.

Memory architecture is another major divider. The HD 8750M uses 1024 MB of DDR3 on a 128-bit bus, yielding 28.80 GB/s of bandwidth. The GTX 980M uses 8 GB of GDDR5 on a 256-bit bus, yielding 160.4 GB/s. That is more than five times the memory capacity and more than five times the bandwidth. The GTX 980M also has a higher effective memory clock at 5 Gbps versus 1800 Mbps for the AMD part.

API support differs as well. The HD 8750M supports DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.170. The GTX 980M supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The higher DirectX feature level and newer Vulkan version on NVIDIA mean better compatibility with modern titles and compute APIs.

Head-to-Head Benchmarks

The only direct comparison in the database is Geekbench OpenCL. The GTX 980M scores 23,832, while the HD 8750M scores 5,970. The delta is 74.9 percent in favor of NVIDIA. This is not a marginal lead; it is a fourfold difference. In raw compute terms, the GTX 980M delivers roughly four times the OpenCL performance of the HD 8750M, which aligns with its fourfold higher shading unit count and much higher clock speeds.

The GTX 980M’s other recorded benchmarks paint a more complete picture. In PassMark G3D, it scores 7,338, which is a strong showing for gaming workloads. Its DirectX 9 score of 125, DirectX 10 score of 35, DirectX 11 score of 57, and DirectX 12 score of 31 are lower, reflecting that older API tests favor different hardware paths. The G2D score of 490 and GPU compute score of 2,816 round out its profile. The HD 8750M has no such additional benchmarks, so the comparison is limited to one test, but that test is decisive.

Looking at the nearest rivals in the database provides context. The HD 8750M’s closest competitors are the NVIDIA Quadro K4000 (average score 5,982, delta of -0.2 percent), the NVIDIA Quadro K620M (5,957, delta of 0.2 percent), the AMD Radeon HD 8730M (5,955, delta of 0.3 percent), and the NVIDIA Quadro K4000M (5,986, delta of -0.3 percent). These deltas are tiny, all within a fraction of a percent, meaning the HD 8750M is essentially tied with these mid-range mobile and workstation GPUs from the same era.

The GTX 980M’s nearest rivals are the NVIDIA GeForce 930A (average score 5,317, delta of -0.2 percent), the NVIDIA GeForce 840M (5,322, delta of -0.3 percent), the NVIDIA GeForce 940M (5,284, delta of 0.5 percent), and the AMD Radeon R7 M445 (5,358, delta of -0.9 percent). These are all lower-tier mobile GPUs, and the GTX 980M’s average score of 5,308 is close to them despite its much higher peak performance. This is because the average includes its low DirectX scores, which pull the mean down. In practice, the GTX 980M would be far ahead of these rivals in gaming, but the database’s averaging methodology obscures that.

FAQ

Q: Which GPU is faster in the recorded benchmark?

A: The NVIDIA GeForce GTX 980M is decisively faster. In Geekbench OpenCL, it scores 23,832 versus 5,970 for the AMD Radeon HD 8750M, a 74.9 percent advantage.

Q: How do their core counts compare?

A: The GTX 980M has 1,536 shading units, 96 TMUs, and 64 ROPs. The HD 8750M has 384 shading units, 24 TMUs, and 8 ROPs. The NVIDIA part has four times the shading units and TMUs, and eight times the ROPs.

Q: What is the memory difference?

A: The GTX 980M uses 8 GB of GDDR5 on a 256-bit bus with 160.4 GB/s bandwidth. The HD 8750M uses 1 GB of DDR3 on a 128-bit bus with 28.80 GB/s bandwidth.

Q: Do they support the same APIs?

A: Both support OpenGL 4.6, but they differ elsewhere. The GTX 980M supports DirectX 12 (12_1) and Vulkan 1.4. The HD 8750M supports DirectX 12 (11_1) and Vulkan 1.2.170.

Q: How do their percentiles compare?

A: The HD 8750M sits at the 34th percentile among all GPUs, while the GTX 980M sits at the 31st percentile. The GTX 980M’s lower percentile is due to its low average benchmark score of 5,308, which is pulled down by its DirectX test results.

Q: What are their production statuses?

A: Both are end-of-life products. The HD 8750M was released on February 25, 2013, and the GTX 980M was released on October 6, 2014.

The Verdict

Based on the recorded data, the NVIDIA GeForce GTX 980M is the clear choice for anyone needing high-performance graphics. Its Geekbench OpenCL score is 74.9 percent higher than the HD 8750M, and its core configuration is vastly superior: four times the shading units, four times the TMUs, eight times the ROPs, and more than five times the memory bandwidth. For gaming, 3D rendering, or any compute-heavy task, the GTX 980M is in a different league.

The AMD Radeon HD 8750M is a much weaker part. Its 384 shading units, 8 ROPs, and 28.80 GB/s of bandwidth place it firmly in entry-level territory. It is suitable for basic desktop productivity, video playback, or older games at low settings, but it cannot handle modern titles or demanding applications. Its percentile ranking of 34 is higher than the GTX 980M’s 31, but that is an artifact of the averaging method, not a sign of real-world competitiveness.

For users choosing between these two, the decision is straightforward. If performance matters, the GTX 980M is the only option. If power consumption, size, or cost are the primary constraints, the HD 8750M may suffice for light workloads, but it will lag severely in any graphics-intensive scenario. The data does not support any other conclusion.

Specification Differences

| Specification | AMD Radeon HD 8750M | NVIDIA GeForce GTX 980M |

| --- | --- | --- |

| Chip | Mars | GM204 |

| Architecture | GCN 1.0 | Maxwell 2.0 |

| Process Node | 28 nm | 28 nm |

| Transistors | 950 million | 5,200 million |

| Die Size | 77 mm² | 398 mm² |

| Base Clock | 775 MHz | 1038 MHz |

| Boost Clock | 825 MHz | 1127 MHz |

| Memory Size | 1024 MB | 8 GB |

| Memory Type | DDR3 | GDDR5 |

| Memory Bus Width | 128 bit | 256 bit |

| Memory Bandwidth | 28.80 GB/s | 160.4 GB/s |

| Shading Units | 384 | 1536 |

| TMUs | 24 | 96 |

| ROPs | 8 | 64 |

| Pixel Rate | 6.600 GPixel/s | 72.13 GPixel/s |

| Texture Rate | 19.80 GTexel/s | 108.2 GTexel/s |

| FP32 Compute | 633.6 GFLOPS | 3.462 TFLOPS |

| DirectX | 12 (11_1) | 12 (12_1) |

| OpenGL | 4.6 | 4.6 |

| Vulkan | 1.2.170 | 1.4 |

| Bus Interface | PCIe 3.0 x8 | MXM-B (3.0) |

| Slot Width | Not specified | MXM Module |

| Release Date | 2013-02-25 | 2014-10-06 |

| Production Status | End-of-life | End-of-life |