NVIDIA GeForce GTX 980 Ti vs NVIDIA GeForce RTX 3080 Mobile Comparison

FAQ

Q: What is the manufacturing process for the NVIDIA GeForce GTX 980 Ti?

A: The GTX 980 Ti is built on TSMC's 28 nm process node, using the GM200 chip. It contains 8,000 million transistors on a 601 mm² die, which results in a transistor density of 13.3 million per square millimeter.

Q: How much memory does the GTX 980 Ti have, and what is its bandwidth?

A: The card ships with 6 GB of GDDR5 memory across a 384-bit bus, delivering 336.6 GB/s of bandwidth. The memory clock runs at 1753 MHz, which the database lists as 7 Gbps effective.

Q: What are the clock speeds of the GTX 980 Ti?

A: The base clock is 1000 MHz with a boost up to 1076 MHz. The shading units run at 2816, the texture mapping units at 176, and the render output units at 96.

Q: What APIs does the GTX 980 Ti support?

A: It supports DirectX 12 (feature level 12_1), OpenGL 4.6, and Vulkan 1.4.

Q: What is the thermal design power and power connector requirement?

A: The board has a 250 W TDP. It requires a dual-slot cooler, one 6-pin and one 8-pin power connector, and a 600 W system power supply is suggested. The interface is PCIe 3.0 x16, with one DVI, one HDMI 2.0, and three DisplayPort 1.2 outputs.

Architecture Differences

The GeForce GTX 980 Ti and the GeForce RTX 3080 Mobile come from different architectural generations. The GTX 980 Ti is based on the Maxwell 2.0 architecture, specifically the GM200 chip fabricated on TSMC's 28 nm process with 8 billion transistors on a 601 mm² die. The RTX 3080 Mobile, in contrast, uses the Ampere architecture with the GA104 chip, built on Samsung's 8 nm node, packing 17.4 billion transistors into a 392 mm² die. The density numbers show the leap: the older card fits 13.3 million transistors per square millimeter, while the newer one reaches 44.4 million.

These architectural differences carry into the compute resources. The Maxwell card has 2816 shading units, 176 texture mapping units, and 96 ROPs. The Ampere chip raises the shading unit count to 6144 and keeps the ROP count at 96, but it adds 192 tensor cores and 48 RT cores. The Maxwell part has no RT or tensor core equivalents. The memory subsystem also differs: the GTX 980 Ti relies on 6 GB GDDR5 on a 384-bit bus, whereas the RTX 3080 Mobile uses 8 GB GDDR6 across a 256-bit bus. The newer card's bandwidth is listed at 448.0 GB/s versus 336.6 GB/s for the older model.

Clock behavior is also different. The GTX 980 Ti runs at a base of 1132 MHz and boosts to 1076 MHz. The RTX 3080 Mobile lists its base at 1110 MHz and a boost of 1545 MHz. The memory operates at 1750 MHz on the Maxwell part and at 1750 MHz on the Ampere part.

Head-to-Head Benchmarks

The recorded data gives a clear edge to the RTX 3080 Mobile in every benchmark category. The largest gap appears in the 3DMark Steel Nomad DX12 test where the GTX 980 Ti scored 1321 against 2644 for the RTX 3080 Mobile, a difference of 50% in favor of the newer card.

The Geekbench OpenCL test shows a similar pattern. The older card produces an OpenCL score of 43513, while the RTX 3080 Mobile reaches 104831. The RTX is 58.5% ahead. In the Geekbench Vulkan test the margin shrinks but remains large: 47724 for the GTX 980 Ti versus 104066 for the RTX 3080 Mobile, meaning the RTX part is 54.1% faster.

Across the full suite, the GTX 980 Ti never wins a head-to-head round. The RTX 3080 Mobile wins all three, and its smallest victory is still above 50% (the 3DMark Steel Nomad at exactly -50.0%, and the Vulkan result at -54.1%).

The Verdict

The benchmark data is decisive. The NVIDIA GeForce GTX 980 Ti is an older Maxwell architecture card with a large memory bus and high TDP (250 W), but it is firmly placed in the slower tier. Its 6 GB of GDDR5 and 336.6 GB/s of bandwidth are still respectable, but the raw shading throughput of 6.060 TFLOPS FP32 falls well behind.

The RTX 3080 Mobile, on the other hand, is a far denser chip. Its Ampere architecture with 6144 shaders, 192 tensor cores, and 48 RT cores, plus 448.0 GB/s of GDDR6 bandwidth, puts it in a completely different performance class. The 18.98 TFLOPS FP32 figure is roughly 3 times the FP32 throughput of the GTX 980 Ti. In every recorded test, the RTX 3080 Mobile wins by more than 50 percentage points.

Which one to pick depends entirely on what the workload requires. If the task is legacy DirectX 9/10/11-era titles, or if power targets and PCIe 3.0 are hard constraints, the GTX 980 Ti is a proven, end-of-life Maxwell card. For anything modern, especially DirectX 12 Ultimate, Vulkan or OpenCL workloads, the RTX 3080 Mobile is the decisive choice: it doubles or triples the frames, it has the newer feature set, and it is an end-of-life mobile part that can still run at a much lower 115 W TDP.

Specification Differences

| Field | NVIDIA GeForce GTX 980 Ti | NVIDIA GeForce RTX 3080 Mobile |

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

| Chip | GM200 | GA104 |

| Architecture | Maxwell 2.0 | Ampere |

| Process | 28 nm | 8 nm |

| Transistors | 8,000 million | 17,400 million |

| Die size | 601 mm² | 392 mm² |

| Transistor density | 13.3M / mm² | 44.4M / mm² |

| Memory | 6 GB GDDR5 | 8 GB GDDR6 |

| Bus width | 384 bit | 256 bit |

| Bandwidth | 336.6 GB/s | 448.0 GB/s |

| FP32 | 6.060 TFLOPS | 18.98 TFLOPS |

| Shading units | 2816 | 6144 |

| Tensor cores | None | 192 |

| RT cores | None | 48 |

| TDP | 250 W | 115 W |

Where Each One Wins

The RTX 3080 Mobile dominates the tests and features in every workload recorded in the database. It wins all three head-to-head comparisons, and the margin is not small: it is 50% to 58.5% ahead in the recorded tests. It wins in DirectX 12-era workloads, OpenCL compute, and Vulkan rendering. It also brings the tensor cores and RT cores that the GTX 980 Ti completely lacks, plus 8 GB of GDDR6 memory and nearly 33% more memory bandwidth (448.0 GB/s vs 336.6 GB/s). Its 115 W TDP also ensures it can be powered in laptops, whereas the 250 W GTX 980 Ti is a desktop-only board with a dual-slot cooler and external power inputs.

The GTX 980 Ti has a narrow place. For a user running legacy DX11/OpenGL titles, or constrained to a PCIe 3.0 platform, or needing the 6 GB of memory, the GTX 980 Ti remains a functional product, but it is end-of-life. The RTX 3080 Mobile is the better card for anyone who wants the highest fps in modern titles, wants to use the tensor cores, or wants to run within a small power budget. The data shows the 3080 Mobile dominating by a wide margin, and its feature set is simply more complete.