NVIDIA GeForce GTX 480 vs NVIDIA GeForce GTX 770 Comparison

FAQ

Q: How much faster is the GeForce GTX 770 than the GeForce GTX 480 in the only shared benchmark?

A: In Geekbench OpenCL, the GTX 770 scores 15,707 points against 13,300 for the GTX 480, a lead of 18.1% for the newer card.

Q: Which card has the higher average benchmark score?

A: The GTX 770 has an average benchmark score of 14,747, while the GTX 480 averages 13,300. The GTX 770 sits at the 57th percentile of all GPUs, while the GTX 480 sits at the 53rd percentile.

Q: What is the closest rival to the GTX 770?

A: The AMD Radeon RX 5500 XT is the nearest rival with an average score of 14,692, just 0.4% behind. The NVIDIA Quadro M2000 is 1.5% behind, while the GeForce GTX 660 Ti and AMD Radeon Pro 560X are 2.1% and 2.2% ahead, respectively.

Q: What is the closest rival to the GTX 480?

A: The AMD Radeon Pro 555X is the closest, with an average score of 13,321, which is 0.2% ahead of the GTX 480. The AMD FirePro M6100 and Radeon RX 5500M both sit 0.4% behind, and the AMD Radeon HD 8950M is 0.6% behind.

Q: Do both cards support DirectX 12?

A: Yes, both support DirectX 12 (11_0) and OpenGL 4.6. However, the GTX 770 supports Vulkan 1.2.175, while the GTX 480 has no Vulkan support recorded.

Q: Which card has the higher launch MSRP?

A: The GeForce GTX 480 had a launch MSRP of 499 USD, while the GeForce GTX 770 had a launch MSRP of 399 USD.

Architecture Differences

The GeForce GTX 770 uses the GK104 chip built on Kepler architecture, fabricated on a 28 nm process at TSMC. The GeForce GTX 480 uses the GF100 chip built on Fermi architecture, also from TSMC but on a 40 nm process. This process shrink is significant: the GTX 770 packs 3,540 million transistors into a 294 mm² die, yielding a transistor density of 12.0 million transistors per square millimeter. The GTX 480, by contrast, contains 3,100 million transistors on a much larger 529 mm² die, giving a transistor density of just 5.9 million per square millimeter. The newer chip nearly doubles the density, which explains how it delivers far more compute resources in roughly the same physical footprint.

The shading unit count differs substantially. The GTX 770 has 1,536 shading units, 128 texture mapping units, and 32 raster output pipelines. The GTX 480 has 480 shading units, 60 TMUs, and 48 ROPs. The GTX 770 has 3.2 times more shaders and over twice the texture units, while the GTX 480 has 50% more ROPs. These structural differences drive distinct performance profiles: the GTX 770 excels at shader-heavy and texture-heavy workloads, while the GTX 480 has an advantage in pixel-fill operations relative to its compute throughput.

Memory architecture also diverges. The GTX 770 has 2 GB of GDDR5 on a 256-bit bus, with memory clocked at 1753 MHz for 7 Gbps effective and bandwidth of 224.4 GB/s. The GTX 480 has 1536 MB of GDDR5 on a wider 384-bit bus, memory clocked at 924 MHz for 3.7 Gbps effective, yielding 177.4 GB/s. The GTX 770 has 47 GB/s more bandwidth despite the narrower bus, thanks to much faster memory clocks.

Clock behavior differs as well. The GTX 770 has a base clock of 1046 MHz and a boost clock of 1085 MHz. The GTX 480 has no base or boost clock listed; only its memory clock is recorded. The GTX 770 also supports PCIe 3.0 x16, while the GTX 480 uses PCIe 2.0 x16. Display outputs show the generational gap: the GTX 770 offers 2x DVI, 1x HDMI 1.4a, and 1x DisplayPort 1.2, while the GTX 480 offers 2x DVI and 1x mini-HDMI 1.3a.

Power characteristics are close but not identical. The GTX 770 has a TDP of 230 W with a suggested PSU of 550 W. The GTX 480 has a TDP of 250 W and requires a 600 W PSU. Both use the same power connector configuration: 1x 6-pin plus 1x 8-pin. Both are dual-slot cards measuring 267 mm (10.5 inches) in length; the GTX 770 adds full dimensions of 111 mm height and 38 mm width, while the GTX 480 lists no height or width.

The Verdict

The data points to the GeForce GTX 770 as the stronger card overall. Its average benchmark score of 14,747 versus 13,300 for the GTX 480 is a 10.9% advantage on the aggregate metric. In the only direct head-to-head test, Geekbench OpenCL, the GTX 770 wins by 18.1%. The percentile ranking reinforces this: the GTX 770 sits at the 57th percentile of all GPUs, four percentage points above the GTX 480 at the 53rd percentile.

The GTX 770 also has the architectural advantages that typically matter for longevity: a smaller process node, higher memory bandwidth, double the memory capacity, and Vulkan support. The GTX 480, however, is not without merit. It has more ROPs (48 versus 32) and a wider memory bus (384-bit versus 256-bit), which historically benefits certain pixel-bound workloads. But the benchmark evidence shows no test where the GTX 480 wins. The wins tally is 1 for the GTX 770 and 0 for the GTX 480.

For users choosing between these two end-of-life cards, the GTX 770 is the clear pick for general compute and most gaming workloads. The GTX 480 remains relevant only for scenarios that specifically favor its higher ROP count, but the recorded data does not include a test that demonstrates such an advantage.

Specification Differences

| Specification | GeForce GTX 770 | GeForce GTX 480 |

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

| Architecture | Kepler | Fermi |

| Chip | GK104 | GF100 |

| Process node | 28 nm | 40 nm |

| Transistors | 3,540 million | 3,100 million |

| Die size | 294 mm² | 529 mm² |

| Transistor density | 12.0M / mm² | 5.9M / mm² |

| Shading units | 1536 | 480 |

| TMUs | 128 | 60 |

| ROPs | 32 | 48 |

| Memory size | 2 GB | 1536 MB |

| Memory bus | 256 bit | 384 bit |

| Memory clock | 1753 MHz (7 Gbps effective) | 924 MHz (3.7 Gbps effective) |

| Memory bandwidth | 224.4 GB/s | 177.4 GB/s |

| Pixel rate | 34.72 GPixel/s | 21.03 GPixel/s |

| Texture rate | 138.9 GTexel/s | 42.06 GTexel/s |

| FP32 | 3.333 TFLOPS | 1,345.0 GFLOPS |

| TDP | 230 W | 250 W |

| Suggested PSU | 550 W | 600 W |

| Bus interface | PCIe 3.0 x16 | PCIe 2.0 x16 |

| Display outputs | 2x DVI, 1x HDMI 1.4a, 1x DisplayPort 1.2 | 2x DVI, 1x mini-HDMI 1.3a |

| Vulkan | 1.2.175 | Not supported |

| Release date | 2013-05-29 | 2010-03-25 |

| Launch MSRP | 399 USD | 499 USD |

Head-to-Head Benchmarks

The only shared benchmark between these two cards is Geekbench OpenCL. The GTX 770 scores 15,707 points, while the GTX 480 scores 13,300 points. The delta is 18.1% in favor of the GTX 770. This is the sole recorded head-to-head result, and it fully determines the win tally.

The OpenCL result aligns with the broader compute specifications. The GTX 770 delivers 3.333 TFLOPS FP32 performance, while the GTX 480 delivers 1,345.0 GFLOPS (1.345 TFLOPS). The GTX 770 has roughly 2.5 times the raw FP32 throughput, which explains the 18.1% OpenCL advantage despite the GTX 480 having a wider memory bus and more ROPs. The GTX 770 also has a texture rate of 138.9 GTexel/s versus 42.06 GTexel/s for the GTX 480, a 3.3 times difference that would likely appear in texture-bound workloads.

The pixel rates tell a different story. The GTX 770 achieves 34.72 GPixel/s, while the GTX 480 achieves 21.03 GPixel/s. Despite having fewer ROPs, the GTX 770 still produces 65% more pixel throughput, likely due to its much higher clock speeds and architectural efficiency. The GTX 480's 48 ROPs cannot compensate for its lower clocks and older architecture.

In terms of memory, the GTX 770 has 224.4 GB/s bandwidth against 177.4 GB/s for the GTX 480, a 26.5% advantage. The GTX 770 also has more memory (2 GB versus 1536 MB), which matters for modern workloads that exceed the older card's capacity.

The average benchmark scores provide additional context. The GTX 770 averages 14,747 points across its recorded tests (Geekbench Metal, OpenCL, and Vulkan), while the GTX 480 averages 13,300 points from its single OpenCL result. The GTX 770's percentile rank of 57 versus the GTX 480's 53 confirms that the newer card sits higher in the overall distribution of all GPUs.

Where Each One Wins

The GeForce GTX 770 wins in every recorded category. It leads in the single head-to-head benchmark by 18.1%, has a higher average score by 1,447 points, and holds a four-point percentile advantage. Its strengths are clear: nearly 2.5 times the FP32 compute, 3.3 times the texture fill rate, 65% higher pixel rate, and 26.5% more memory bandwidth. For compute workloads, shader-heavy applications, and modern game titles that use more than 1536 MB of video memory, the GTX 770 is the better choice.

The GeForce GTX 480 does not win any recorded benchmark. Its theoretical advantages are limited to a wider memory bus (384-bit versus 256-bit) and more ROPs (48 versus 32). In practice, the recorded pixel rate shows the GTX 770 still outperforms it in fill-rate terms. The GTX 480's larger die, older 40 nm process, and higher TDP of 250 W do not translate into any measured victory. Its only historical role would be in workloads that specifically favor its ROP count, but no such test appears in the database results.

For users prioritizing compute performance, the GTX 770 is the definitive pick. For users constrained by power delivery, the GTX 770 also has the edge with a 230 W TDP and 550 W suggested PSU versus 250 W and 600 W for the GTX 480. The GTX 480 launched earlier (March 2010 versus May 2013) and carried a higher launch MSRP of 499 USD versus 399 USD, yet it delivers less performance in every measured metric. The data is unambiguous: the GTX 770 outperforms the GTX 480 across the board.