AMD Radeon 860M vs NVIDIA GeForce RTX 2080 Comparison

AMD Radeon 860M vs NVIDIA GeForce RTX 2080

The database comparison between the AMD Radeon 860M and the NVIDIA GeForce RTX 2080 is a study in contrast, pitting a modern low-power integrated processor against an older, high-performance discrete graphics card. The recorded benchmark data shows a decisive performance gap, with the RTX 2080 dominating both shared test workloads. However, the architectural and efficiency differences are stark, making this a comparison of two very different design philosophies rather than a close contest.

Head-to-Head Benchmarks

The head-to-head results are unambiguous. In the Geekbench OpenCL test, the NVIDIA GeForce RTX 2080 scored 91,313, while the AMD Radeon 860M managed 22,759. This represents a 75.1% deficit for the 860M, meaning the RTX 2080 delivers roughly four times the compute throughput in this workload. The gap is nearly as pronounced in the Geekbench Vulkan test, where the RTX 2080 posted 107,797 against the 860M’s 30,043, a 72.1% shortfall. In both cases, the RTX 2080 is the clear winner, and the margins are not close enough to be considered competitive.

Looking at the broader average benchmark scores, the RTX 2080 holds an average of 22,895 across its tested workloads, while the 860M averages 26,401. This is an interesting inversion, as the 860M’s average is actually 15.3% higher than the RTX 2080’s, despite losing the head-to-head tests. The reason for this is that the two GPUs are measured on different benchmark suites. The 860M’s average is derived solely from its two Geekbench scores, which are both relatively high for an integrated part. The RTX 2080’s average includes a wider range of tests, including several Passmark legacy DirectX workloads where it scores very low (e.g., 72 in DirectX 12, 136 in DirectX 10), dragging its average down. This highlights the importance of looking at specific test results rather than aggregate scores when comparing across generations.

The RTX 2080’s percentile ranking among all GPUs is 68, while the 860M sits at 72. This means the 860M is in a higher percentile of overall performance, but this is again skewed by the limited test set. In any direct comparison of the shared benchmarks, the RTX 2080 is faster by a wide margin. The data shows that the RTX 2080 is the superior performer in raw compute, and the 860M’s higher average score is a statistical artifact of its lighter test load.

Where Each One Wins

The NVIDIA GeForce RTX 2080 wins every head-to-head benchmark recorded in the database. It dominates in both OpenCL and Vulkan compute workloads, which are representative of general-purpose GPU tasks and modern graphics APIs. The RTX 2080’s 10.07 TFLOPS of FP32 performance, 109.4 GPixel/s pixel rate, and 314.6 GTexel/s texture rate are all significantly higher than the 860M’s 3.072 TFLOPS, 48.00 GPixel/s, and 96.00 GTexel/s. For any task that relies on raw shading, rasterization, or compute throughput, the RTX 2080 is the clear choice.

The AMD Radeon 860M does not win any benchmark in this comparison, but it has its own advantages that are not captured in the performance scores. The most obvious is power consumption. The 860M has a TDP of just 15 W, compared to the RTX 2080’s 215 W. This is a 14-fold difference in power draw, which makes the 860M suitable for ultra-portable devices with no dedicated power connectors, whereas the RTX 2080 requires a 550 W recommended PSU and dual power connectors. The 860M also uses system-shared memory, which is not as fast as the RTX 2080’s 8 GB of GDDR6 on a 256-bit bus with 448.0 GB/s of bandwidth, but it eliminates the need for a separate VRAM pool. The 860M is also smaller, as an integrated graphics processor, compared to the RTX 2080’s dual-slot, 267 mm long expansion card.

For a user prioritizing battery life, portability, and a compact form factor, the 860M is the only viable option. For a desktop user who needs maximum performance and has the power budget and physical space, the RTX 2080 is the only option. There is no overlap in their intended use cases.

Architecture Differences

The AMD Radeon 860M is built on TSMC’s 4 nm process node and uses the RDNA 3.5 architecture, part of the Navi III IGP generation for Strix Point Mobile. It is an integrated GPU with 512 shading units, 32 texture mapping units, 16 ROPs, and 8 ray tracing cores. Its base clock is 600 MHz with a boost clock of 3000 MHz. The chip is called Krackan Point, and it supports PCIe 4.0 x8. The 860M is a very modern, power-efficient design that shares system memory for all graphics operations.

The NVIDIA GeForce RTX 2080 is built on TSMC’s 12 nm process and uses the Turing architecture, part of the GeForce 20 series. It is a massive discrete GPU with 2944 shading units, 184 TMUs, 64 ROPs, 46 ray tracing cores, and 368 tensor cores. The die size is 545 mm² with 13,600 million transistors, giving a transistor density of 25.0M per mm². Its base clock is 1515 MHz with a boost clock of 1710 MHz. The RTX 2080 uses 8 GB of GDDR6 memory on a 256-bit bus, with a bandwidth of 448.0 GB/s and an effective memory clock of 14 Gbps. It connects via PCIe 3.0 x16.

The process node difference is significant: 4 nm versus 12 nm. This explains the massive disparity in power consumption and die size. The 860M achieves its performance with a much smaller, more efficient design. The RTX 2080 has far more compute resources, but it also has a much higher power draw and a larger physical footprint. The RTX 2080 includes tensor cores, which are absent from the 860M, making it more capable for AI and machine learning workloads. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The RTX 2080 was released on 2018-09-19 and is now end-of-life, while the 860M was released on 2025-02-28 and is still active production.

FAQ

Q: Which GPU is faster in raw compute performance?

A: The NVIDIA GeForce RTX 2080 is significantly faster. In Geekbench OpenCL, it scores 91,313 versus the AMD Radeon 860M’s 22,759, a 75.1% lead. In Geekbench Vulkan, it scores 107,797 versus 30,043, a 72.1% lead.

Q: Why does the AMD Radeon 860M have a higher average benchmark score than the RTX 2080?

A: The 860M has an average score of 26,401, while the RTX 2080 averages 22,895. This is because the 860M’s average is based only on two Geekbench tests, which are favorable to it. The RTX 2080’s average includes several legacy Passmark DirectX tests with very low scores, such as 72 in DirectX 12 and 136 in DirectX 10, which lower its overall average.

Q: What are the power consumption differences?

A: The AMD Radeon 860M has a TDP of 15 W, while the NVIDIA GeForce RTX 2080 has a TDP of 215 W. The RTX 2080 also requires a 550 W recommended PSU and uses 1x 6-pin and 1x 8-pin power connectors, whereas the 860M is an IGP with no power connectors.

Q: How does memory configuration differ between the two?

A: The RTX 2080 has 8 GB of dedicated GDDR6 memory on a 256-bit bus with 448.0 GB/s bandwidth. The 860M uses system-shared memory, with its size, type, and bus width all listed as "System Shared" and bandwidth as "System Dependent."

Q: Are there any advantages to the AMD Radeon 860M besides power?

A: The 860M is built on a much more advanced 4 nm process node compared to the RTX 2080’s 12 nm node. It is an integrated solution, meaning it takes up no expansion slot space and is suitable for portable devices. Its boost clock is higher at 3000 MHz versus 1710 MHz for the RTX 2080.

Q: Which GPU supports newer PCIe standards?

A: The AMD Radeon 860M supports PCIe 4.0 x8, while the NVIDIA GeForce RTX 2080 supports the older PCIe 3.0 x16 standard.

The Verdict

The NVIDIA GeForce RTX 2080 is the definitive winner in performance. The data shows it is roughly 3 to 4 times faster than the AMD Radeon 860M in both OpenCL and Vulkan workloads. For any user building a desktop system for gaming, content creation, or compute-heavy tasks, the RTX 2080 is the only choice between these two, provided the system can accommodate its 215 W TDP, dual-slot size, and power connector requirements. Its 10.07 TFLOPS FP32 performance and 448.0 GB/s memory bandwidth are in a different class entirely.

The AMD Radeon 860M is not a competitor in raw speed, but it is a superior solution for a completely different use case. Its 15 W TDP and integrated design make it ideal for thin-and-light laptops where battery life and thermals are paramount. It offers modern features like RDNA 3.5 and a 3000 MHz boost clock, and it is built on a current-generation 4 nm process. It will handle light gaming and general productivity, but it will not satisfy users seeking high frame rates in demanding titles.

The verdict is straightforward: choose the RTX 2080 for maximum performance in a desktop environment, and choose the 860M for an efficient, portable integrated solution. They do not target the same user, and the benchmark results simply confirm that the desktop-class discrete card is in a higher performance tier.