AMD Radeon RX 6600M vs NVIDIA GeForce GTX 980 Ti Comparison

Head-to-Head Benchmarks

The benchmark data shows a decisive victory for the AMD Radeon RX 6600M across all four recorded head-to-head tests, with the NVIDIA GeForce GTX 980 Ti failing to secure a single win. The largest margin appears in the Geekbench Metal test, where the RX 6600M scores 92,237 against the GTX 980 Ti's 19,520, a delta of -78.8% from the NVIDIA card's perspective. This is not merely a marginal lead; it represents a fundamental generational gap in compute efficiency and API-level performance.

The Geekbench OpenCL results tell a similar story, though with a narrower gap. The RX 6600M posts 67,765 versus the GTX 980 Ti's 43,513, a 35.8% deficit for the older NVIDIA part. OpenCL is a cross-vendor workload, so this result reflects raw shader throughput and memory subsystem behavior rather than driver optimizations for a specific API. The RX 6600M's advantage here aligns with its higher FP32 throughput (8.659 TFLOPS versus 6.060 TFLOPS), but the magnitude of the win suggests architectural efficiency plays a role beyond raw numbers.

Vulkan performance shows the RX 6600M leading by 35.3%, with scores of 73,740 versus 47,724. Vulkan is a low-level API that exposes hardware capabilities directly, so this result indicates that the RDNA 2.0 architecture's async compute and geometry processing pipelines are measurably more effective than Maxwell 2.0's. The 3DMark Steel Nomad DX12 test is the closest contest: the RX 6600M scores 1,495 against the GTX 980 Ti's 1,321, a modest 11.6% lead. DX12 is the one area where the older NVIDIA card remains competitive, likely due to its larger 384-bit memory bus and 96 ROPs, which help in bandwidth-sensitive rasterization workloads.

Across the four tests, the RX 6600M's average benchmark score is 23,273, while the GTX 980 Ti averages 28,020. The discrepancy between the head-to-head results and the overall averages is notable: the GTX 980 Ti holds a higher aggregate score because its benchmark pool includes Geekbench OpenCL (43,513) and Vulkan (47,724) results that are respectable for its era, but the RX 6600M's additional PassMark tests (DirectX 9, 10, 11, 12, G2D, G3D, and GPU Compute) pull its average down. In direct competition, however, the RX 6600M wins every time.

Architecture Differences

The two GPUs come from different design philosophies separated by six years of process technology and architectural evolution. The GTX 980 Ti uses the GM200 chip built on TSMC's 28 nm node, housing 8,000 million transistors across a 601 mm² die. That translates to a transistor density of 13.3 million per square millimeter. The RX 6600M employs the Navi 23 chip on TSMC's 7 nm process, packing 11,060 million transistors into a 237 mm² die, achieving a density of 46.7 million per square millimeter. The density advantage is roughly 3.5x, which explains how AMD fits more transistors in less than half the silicon area.

The GTX 980 Ti's Maxwell 2.0 architecture relies on 2,816 shading units, 176 TMUs, and 96 ROPs. The RX 6600M counters with 1,792 shading units, 112 TMUs, and 64 ROPs. Despite having fewer execution units, the RX 6600M delivers higher pixel rate (154.6 GPixel/s versus 103.3 GPixel/s) and texture rate (270.6 GTexel/s versus 189.4 GTexel/s). This is a direct consequence of the RX 6600M's much higher clock speeds: its base clock is 2068 MHz and boost reaches 2416 MHz, while the GTX 980 Ti operates at 1000 MHz base and 1076 MHz boost. The RX 6600M also has a game clock of 2177 MHz, a feature absent from the NVIDIA card.

Memory configurations differ substantially. The GTX 980 Ti uses 6 GB of GDDR5 on a 384-bit bus, producing 336.6 GB/s of bandwidth at 7 Gbps effective. The RX 6600M uses 8 GB of GDDR6 on a 128-bit bus, yielding 224.0 GB/s at 14 Gbps effective. The NVIDIA card has 50% more bandwidth, but the AMD part has 33% more capacity. For modern games with large texture sets, the RX 6600M's capacity advantage may offset its bandwidth deficit.

The RX 6600M includes 28 ray tracing cores, a feature entirely absent from the GTX 980 Ti. It also supports DirectX 12 Ultimate (12_2), whereas the NVIDIA card is limited to DirectX 12 (12_1). Both support OpenGL 4.6 and Vulkan 1.4. The RX 6600M has a TDP of 100 W and uses no external power connectors, as it is an IGP for mobile systems. The GTX 980 Ti draws 250 W, requires a 600 W power supply, and uses 1x 6-pin plus 1x 8-pin connectors. The NVIDIA card is a dual-slot 267 mm long desktop part, while the RX 6600M is a portable-device-dependent IGP with no listed dimensions.

FAQ

Q: Which GPU is faster in the 3DMark Steel Nomad DX12 benchmark?

A: The AMD Radeon RX 6600M wins with a score of 1,495 versus the NVIDIA GeForce GTX 980 Ti's 1,321, a margin of 11.6%.

Q: How large is the performance gap in Geekbench Metal?

A: The RX 6600M scores 92,237 compared to the GTX 980 Ti's 19,520, making the NVIDIA card 78.8% slower in this test.

Q: Does the GTX 980 Ti support ray tracing?

A: No. The GTX 980 Ti has no ray tracing cores, while the RX 6600M includes 28 ray tracing cores.

Q: What are the power requirements for each card?

A: The GTX 980 Ti has a TDP of 250 W and requires a 600 W power supply with 1x 6-pin and 1x 8-pin connectors. The RX 6600M has a TDP of 100 W and uses no power connectors.

Q: Which GPU has more memory bandwidth?

A: The GTX 980 Ti has higher bandwidth at 336.6 GB/s, using 6 GB of GDDR5 on a 384-bit bus. The RX 6600M offers 224.0 GB/s with 8 GB of GDDR6 on a 128-bit bus.

Q: What is the transistor density difference?

A: The RX 6600M achieves 46.7 million transistors per square millimeter on a 7 nm process, while the GTX 980 Ti has 13.3 million per square millimeter on a 28 nm process.

Specification Differences

The two GPUs differ across nearly every specification category. The GTX 980 Ti uses the GM200 chip with Maxwell 2.0 architecture, while the RX 6600M uses Navi 23 with RDNA 2.0. The process nodes are 28 nm versus 7 nm, and the transistor counts are 8,000 million versus 11,060 million. Die sizes are 601 mm² versus 237 mm².

Clock speeds show the RX 6600M's advantage: base 2068 MHz versus 1000 MHz, boost 2416 MHz versus 1076 MHz, and game clock 2177 MHz (absent on the NVIDIA card). Memory clocks are similar in raw frequency (1753 MHz versus 1750 MHz), but effective rates differ at 7 Gbps versus 14 Gbps. Memory size is 6 GB versus 8 GB, types are GDDR5 versus GDDR6, bus widths are 384-bit versus 128-bit, and bandwidth is 336.6 GB/s versus 224.0 GB/s.

Compute resources: shading units 2816 versus 1792, TMUs 176 versus 112, ROPs 96 versus 64, and RT cores 28 (only on AMD). Pixel rates are 103.3 GPixel/s versus 154.6 GPixel/s, texture rates 189.4 GTexel/s versus 270.6 GTexel/s, and FP32 performance 6.060 TFLOPS versus 8.659 TFLOPS. The RX 6600M also has FP16 at 17.32 TFLOPS (2:1), which the GTX 980 Ti lacks.

Power and physical specs: TDP 250 W versus 100 W, slot width dual-slot versus IGP, power connectors 1x 6-pin + 1x 8-pin versus none, and suggested PSU 600 W versus none. The bus interface is PCIe 3.0 x16 versus PCIe 4.0 x8. Display outputs are 1x DVI, 1x HDMI 2.0, and 3x DisplayPort 1.2 versus portable-device-dependent outputs. DirectX support is 12 (12_1) versus 12 Ultimate (12_2). Dimensions for the GTX 980 Ti are 267 mm length, 111 mm height, and 40 mm width; the RX 6600M has no listed dimensions.

Where Each One Wins

The AMD Radeon RX 6600M wins in every direct benchmark comparison. Its dominance is most pronounced in Geekbench Metal, where it is 78.8% faster, and in OpenCL and Vulkan, where it leads by approximately 35%. These are compute-oriented workloads that leverage the RDNA 2.0 architecture's higher clock speeds and FP32 throughput. The RX 6600M is also the clear choice for modern API support, featuring DirectX 12 Ultimate, ray tracing cores, and FP16 compute capabilities.

The RX 6600M's 8 GB of memory gives it an edge in capacity-sensitive scenarios, and its 100 W TDP makes it suitable for mobile implementations where power efficiency is critical. Its PCIe 4.0 x8 interface provides higher per-lane bandwidth than the GTX 980 Ti's PCIe 3.0 x16, which can benefit data transfer in systems that support the newer standard.

The NVIDIA GeForce GTX 980 Ti retains advantages in specific hardware characteristics, even though it loses all recorded benchmarks. Its 384-bit memory bus and 336.6 GB/s bandwidth exceed the RX 6600M's 128-bit bus and 224.0 GB/s. For workloads that are heavily bandwidth-bound, such as high-resolution texture streaming or certain compute kernels, the GTX 980 Ti's memory subsystem could theoretically offer better performance, though the benchmark data does not capture such a scenario.

The GTX 980 Ti also has more ROPs (96 versus 64), which historically helps with fill-rate-limited tasks at high resolutions. Its desktop form factor with dual-slot cooling and multiple display outputs (DVI, HDMI 2.0, and three DisplayPort 1.2) makes it suitable for multi-monitor setups or legacy connectivity needs. The RX 6600M, as a mobile IGP, depends entirely on the host device for display outputs.

For users considering these GPUs today, the data strongly favors the RX 6600M for general performance and modern feature support. The GTX 980 Ti's only practical wins are in raw memory bandwidth and ROP count, which do not translate to benchmark victories in any of the four recorded tests. The RX 6600M's 11.6% lead in 3DMark Steel Nomad DX12 is the closest contest, suggesting that the GTX 980 Ti remains competitive in pure DX12 rasterization, but this is insufficient to overcome the AMD part's advantages elsewhere.