NVIDIA GeForce GTX 1080 vs NVIDIA GeForce GTX 870M Comparison

Head-to-Head Benchmarks

The recorded data includes two direct comparison tests between the NVIDIA GeForce GTX 1080 and the NVIDIA GeForce GTX 870M, and the GTX 1080 wins both by a wide margin. In Geekbench Metal, the GTX 1080 scores 23,824 against the GTX 870M’s 7,288, a 226.9% advantage. In Geekbench OpenCL, the gap widens further: the GTX 1080 posts 51,204 versus 12,630, which is 305.4% higher. These are not marginal improvements; the GTX 1080 delivers more than triple the OpenCL score of the older mobile part.

Looking at the broader benchmark picture, the GTX 1080’s average benchmark score across all recorded tests is 11,960. That places it at the 51st percentile of all GPUs in the database. Its nearest rivals in the database are the NVIDIA GeForce GTX 960A at 11,998 (0.3% lower), the AMD Radeon RX 6500 XT at 11,842 (1% lower), the NVIDIA GeForce GTX 1660 at 11,680 (2.4% lower), and the AMD Radeon RX 7800 XT at 11,627 (2.9% lower). So the GTX 1080 sits in a tight cluster, slightly behind the GTX 960A but ahead of several modern desktop cards.

The GTX 870M, by contrast, has an average benchmark score of 9,959, placing it at the 48th percentile. Its nearest rivals include the AMD Radeon Pro 5300M at 10,013 (0.5% higher), the NVIDIA Quadro K5100M at 10,043 (0.8% higher), the AMD Radeon R9 M375 at 10,070 (1.1% higher), and the NVIDIA Quadro 6000 at 9,846 (1.1% lower). The GTX 870M essentially trades blows with those parts, staying within a few percentage points of each. The delta between the two cards being compared here is far larger than any intra-tier gap: the GTX 1080 leads by roughly 20% in average score, and by 226.9% to 305.4% in the two shared tests.

The GTX 1080 also has a much richer benchmark history in the database. It has recorded scores in 3DMark Steel Nomad DX12 (1,560), Geekbench Metal (23,824), Geekbench OpenCL (51,204), Geekbench Vulkan (30,398), Passmark DX10 (93), Passmark DX11 (124), Passmark DX12 (55), Passmark DX9 (211), Passmark G2D (888), Passmark G3D (15,586), and Passmark GPU Compute (7,614). The GTX 870M only has two recorded entries: Geekbench Metal and OpenCL, both far below the GTX 1080’s corresponding numbers. The absence of other test results for the GTX 870M limits direct comparisons, but the two available metrics are unambiguous.

Architecture Differences

The two GPUs come from completely different architectural generations. The GTX 1080 uses the GP104 chip on the Pascal architecture, fabricated on a 16 nm process at TSMC. The GTX 870M uses the GK104 chip on the Kepler architecture, also from TSMC but on a 28 nm process. This process shrink is a major factor: the GTX 1080 packs 7,200 million transistors into a 314 mm² die, giving a transistor density of 22.9 million per square millimeter. The GTX 870M has 3,540 million transistors on a 294 mm² die, for a density of 12.0 million per square millimeter. The newer process allows nearly double the transistor density in a similar physical footprint.

Shader resources differ substantially. The GTX 1080 has 2,560 shading units, 160 texture mapping units, and 64 ROPs. The GTX 870M has 1,344 shading units, 112 TMUs, and only 24 ROPs. That is nearly double the shading units and almost triple the ROP count on the GTX 1080. Pixel rate for the GTX 1080 is 110.9 GPixel/s versus 27.08 GPixel/s for the GTX 870M. Texture rate is 277.3 GTexel/s versus 108.3 GTexel/s. Floating point performance (FP32) is 8.873 TFLOPS versus 2.599 TFLOPS. The GTX 1080 also supports FP16 at 138.6 GFLOPS (1:64 ratio), while the GTX 870M has no recorded FP16 capability.

Memory configuration is another clear divider. The GTX 1080 uses 8 GB of GDDR5X on a 256-bit bus, with memory clocked at 1251 MHz and 10 Gbps effective, yielding 320.3 GB/s bandwidth. The GTX 870M uses 3 GB of GDDR5 on a 192-bit bus, at 1250 MHz and 5 Gbps effective, for 120.0 GB/s. That is a 2.67x bandwidth advantage for the GTX 1080, plus more than double the memory capacity. The GTX 1080’s memory type (GDDR5X) is also a generation ahead of the GTX 870M’s GDDR5.

Clock speeds differ as well. The GTX 1080 runs at a base clock of 1607 MHz and boost of 1733 MHz. The GTX 870M has a base of 941 MHz and boost of 967 MHz. The GTX 1080’s boost clock is nearly 800 MHz higher. Power draw reflects the performance gap: the GTX 1080 has a TDP of 180 W, while the GTX 870M is rated at 100 W. The GTX 1080 is a dual-slot card requiring a single 8-pin power connector and a 450 W suggested power supply. The GTX 870M is an MXM module with no power connectors, drawing power through the laptop socket.

API support also differs. The GTX 1080 supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The GTX 870M supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175. The DirectX feature level is notably higher on the GTX 1080. Display outputs on the GTX 1080 include 1x DVI, 1x HDMI 2.0, and 3x DisplayPort 1.4a. The GTX 870M’s outputs are listed as “Portable Device Dependent,” reflecting its laptop-oriented MXM form factor. Bus interface is PCIe 3.0 x16 for the GTX 1080 versus MXM-B (3.0) for the GTX 870M.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The GTX 1080 has an average benchmark score of 11,960, while the GTX 870M averages 9,959. That is a lead of roughly 20% for the GTX 1080.

Q: How large is the gap in Geekbench OpenCL?

A: The GTX 1080 scores 51,204 versus 12,630 for the GTX 870M, a delta of 305.4%. The GTX 1080 is more than three times faster in this test.

Q: What are the memory capacities and types?

A: The GTX 1080 has 8 GB of GDDR5X on a 256-bit bus with 320.3 GB/s bandwidth. The GTX 870M has 3 GB of GDDR5 on a 192-bit bus with 120.0 GB/s bandwidth.

Q: Which card has more shading units?

A: The GTX 1080 has 2,560 shading units, compared to 1,344 on the GTX 870M. The GTX 1080 also has 160 TMUs versus 112, and 64 ROPs versus 24.

Q: What is the process node difference?

A: The GTX 1080 is built on a 16 nm process at TSMC, while the GTX 870M uses a 28 nm process, also at TSMC. The GTX 1080 achieves 22.9 million transistors per mm² versus 12.0 million for the GTX 870M.

Q: Do both cards support DirectX 12?

A: Yes, but at different feature levels. The GTX 1080 supports DirectX 12 (12_1), while the GTX 870M supports DirectX 12 (11_0). Both support OpenGL 4.6, but Vulkan versions differ: 1.4 on the GTX 1080 versus 1.2.175 on the GTX 870M.

The Verdict

The data is decisive. For any workload measured in the database, the GTX 1080 is the superior product. In the two shared tests, it wins by 226.9% (Metal) and 305.4% (OpenCL). Its average benchmark score of 11,960 versus 9,959 puts it in a higher performance tier entirely. The GTX 1080 also lands at the 51st percentile of all GPUs, while the GTX 870M sits at the 48th percentile, but that percentile difference understates the real gap because the GTX 870M’s nearest rivals are all within 1.1% of its score, whereas the GTX 1080’s nearest rivals are all within 2.9% but at a much higher absolute level.

The GTX 1080 is the choice for anyone who needs high frame rates, higher resolutions, or compute-heavy tasks. Its 8 GB GDDR5X memory, 320.3 GB/s bandwidth, and 8.873 TFLOPS FP32 performance are all clearly ahead. The GTX 870M, with 3 GB GDDR5, 120.0 GB/s, and 2.599 TFLOPS, is a much older design from 2014, and the data reflects that. The GTX 870M might still be acceptable for light or legacy workloads, but it cannot compete in any metric recorded here. The GTX 1080 wins both head-to-head tests and holds a commanding lead in raw architecture specifications. The verdict is straightforward: pick the GTX 1080 unless the MXM form factor of the GTX 870M is an absolute requirement.

Specification Differences

| Specification | GTX 1080 | GTX 870M |

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

| Chip | GP104 | GK104 |

| Architecture | Pascal | Kepler |

| Process Node | 16 nm | 28 nm |

| Transistors | 7,200 million | 3,540 million |

| Die Size | 314 mm² | 294 mm² |

| Transistor Density | 22.9M / mm² | 12.0M / mm² |

| Base Clock | 1607 MHz | 941 MHz |

| Boost Clock | 1733 MHz | 967 MHz |

| Memory Clock | 1251 MHz (10 Gbps effective) | 1250 MHz (5 Gbps effective) |

| Memory Size | 8 GB | 3 GB |

| Memory Type | GDDR5X | GDDR5 |

| Memory Bus Width | 256 bit | 192 bit |

| Memory Bandwidth | 320.3 GB/s | 120.0 GB/s |

| Shading Units | 2560 | 1344 |

| TMUs | 160 | 112 |

| ROPs | 64 | 24 |

| Pixel Rate | 110.9 GPixel/s | 27.08 GPixel/s |

| Texture Rate | 277.3 GTexel/s | 108.3 GTexel/s |

| FP32 | 8.873 TFLOPS | 2.599 TFLOPS |

| FP16 | 138.6 GFLOPS (1:64) | Not recorded |

| TDP | 180 W | 100 W |

| Slot Width | Dual-slot | MXM Module |

| Power Connectors | 1x 8-pin | None |

| Suggested PSU | 450 W | Not recorded |

| Bus Interface | PCIe 3.0 x16 | MXM-B (3.0) |

| Display Outputs | 1x DVI, 1x HDMI 2.0, 3x DisplayPort 1.4a | Portable Device Dependent |

| DirectX | 12 (12_1) | 12 (11_0) |

| OpenGL | 4.6 | 4.6 |

| Vulkan | 1.4 | 1.2.175 |

| Release Date | 2016-05-26 | 2014-03-11 |

| Launch MSRP | 599 USD | Not recorded |

| Predecessor | GeForce 900 | GeForce 700M |

| Successor | GeForce 20 | GeForce 900M |