AMD Radeon 860M vs NVIDIA GeForce RTX 3080 Ti Mobile Comparison

The GeForce RTX 3080 Ti Mobile dominates the AMD Radeon 860M in every benchmark where both have data. The data shows a decisive NVIDIA victory, with the discrete mobile flagship outperforming the integrated AMD solution by margins that exceed 70%. However, the comparison is not merely about raw speed; it highlights a fundamental divide in power, architecture, and intended use case.

Head-to-Head Benchmarks

The available head-to-head data is limited to two synthetic tests, but the results are unambiguous. In Geekbench OpenCL, the NVIDIA GeForce RTX 3080 Ti Mobile scores 117,866 against the AMD Radeon 860M’s 22,759. That represents a delta of -80.7% for the AMD part, meaning the RTX 3080 Ti Mobile delivers roughly five times the raw compute throughput in this API. This is a generational gap in execution resources: the NVIDIA part has 7,424 shading units versus 512 for AMD, a 14.5x difference in shader count that no clock speed advantage can fully offset.

The Vulkan result tells a similar story, though the margin narrows slightly. The RTX 3080 Ti Mobile posts 107,502, while the Radeon 860M manages 30,043. The -72.1% delta indicates the AMD IGP is closer in this API, but it still trails by a factor of 3.5x. The absolute numbers are stark: 107,502 vs 30,043. This suggests that while the AMD Radeon 860M benefits from its RDNA 3.5 architecture in Vulkan, it cannot overcome the sheer scale of the Ampere-based GA103 chip.

When placed in the broader context of all GPUs, both parts sit in similar percentile territory. The AMD Radeon 860M holds a 72nd percentile ranking, while the RTX 3080 Ti Mobile is at the 71st. Their average benchmark scores are also close in the aggregate: 26,401 for AMD versus 25,740 for NVIDIA. This is a misleading statistic, however, because the averages are calculated across different test suites. The RTX 3080 Ti Mobile’s results include a 19288 Passmark G3D score and an 8471 Passmark GPU Compute score, which are not available for the AMD part. In the only two tests they share, NVIDIA wins both.

The delta percentages are decisive. In OpenCL, the NVIDIA part is 80.7% faster. In Vulkan, it is 72.1% faster. There is no benchmark where the AMD Radeon 860M takes the lead. The data confirms that the RTX 3080 Ti Mobile is in a different performance class, befitting its role as a high-end discrete mobile GPU.

Architecture Differences

The architectural gulf between these two GPUs is vast. The AMD Radeon 860M is an integrated graphics processor (IGP) built on the Krackan Point chip, using the RDNA 3.5 architecture on a 4 nm TSMC process. It belongs to the Navi III IGP generation for Strix Point Mobile. In contrast, the NVIDIA GeForce RTX 3080 Ti Mobile is a discrete part based on the GA103 chip, using the Ampere architecture on an 8 nm Samsung process. The process node difference is significant: 4 nm versus 8 nm, giving AMD a density advantage in principle.

The transistor counts reflect this. NVIDIA’s GA103 packs 22,000 million transistors on a 496 mm² die, yielding a density of 44.4M / mm². AMD does not disclose transistor count or die size for the Krackan Point IGP, but as an integrated solution, it shares a substrate with the CPU, making direct comparison moot. The NVIDIA chip is a massive, standalone die; the AMD part is a slice of a larger processor.

Memory architecture is a core differentiator. The RTX 3080 Ti Mobile has 16 GB of dedicated GDDR6 memory on a 256-bit bus, delivering 512.0 GB/s of bandwidth. The Radeon 860M uses System Shared memory, with bandwidth that is System Dependent. This is a critical distinction: the NVIDIA part has guaranteed, high-speed dedicated VRAM, while the AMD part must contend with system memory for both CPU and GPU workloads. The memory clock for NVIDIA is listed at 2000 MHz, with 16 Gbps effective speed, while AMD’s memory clock is simply "System Shared."

Compute resources are overwhelmingly in NVIDIA’s favor. The RTX 3080 Ti Mobile has 7,424 shading units, 232 TMUs, 96 ROPs, 58 RT cores, and 232 tensor cores. The Radeon 860M has 512 shading units, 32 TMUs, 16 ROPs, and 8 RT cores, with no tensor cores listed. The pixel rate for NVIDIA is 121.0 GPixel/s versus 48.00 GPixel/s for AMD. Texture rate is 292.3 GTexel/s versus 96.00 GTexel/s. FP32 compute is 18.71 TFLOPS versus 3.072 TFLOPS. The ratio is roughly 6:1 in raw throughput.

Power consumption tells the story of intent. The RTX 3080 Ti Mobile is rated at 115 W TDP, while the Radeon 860M is rated at just 15 W. This 100 W difference is the enabling factor for NVIDIA’s performance lead. The AMD part is designed for efficiency and integration; the NVIDIA part for maximum performance in a laptop chassis. Both use PCIe 4.0, but NVIDIA uses x16 lanes while AMD uses x8. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Where Each One Wins

The AMD Radeon 860M wins in efficiency and integration. At 15 W TDP, it is designed for thin-and-light laptops where battery life and thermal management are paramount. Its 4 nm process node gives it a manufacturing advantage, and its System Shared memory means no dedicated VRAM cost. The Radeon 860M’s average benchmark score of 26,401 places it just 0.1% behind the NVIDIA GeForce MX550 in the nearestRivals data, indicating it can handle light gaming and general-purpose GPU tasks. It is a capable IGP for everyday use, multimedia, and esports-level gaming at modest settings.

The NVIDIA GeForce RTX 3080 Ti Mobile wins in every performance metric that matters for demanding applications. Its 16 GB of GDDR6 memory and 512.0 GB/s bandwidth enable high-resolution textures and complex scenes. The 58 RT cores provide hardware ray tracing, and the 232 tensor cores accelerate AI workloads like DLSS. The Passmark scores, though not directly comparable to AMD, show versatility: 19,288 in G3D, 8,471 in GPU Compute, and 818 in G2D. The 3DMark Steel Nomad DX12 score of 2,869 further evidences its modern API strength.

For gamers and creators, the RTX 3080 Ti Mobile is the clear choice. For users who prioritize portability and battery life, the Radeon 860M is the rational pick. The data shows no overlap: the NVIDIA part is 72-81% faster in shared benchmarks, but consumes nearly 8x the power. The Radeon 860M’s nearestRivals include the RTX 5060 (deltaPct 0.3%), indicating it competes with entry-level discrete GPUs, not high-end ones like the RTX 3080 Ti Mobile.

FAQ

Q: Which GPU is faster in Geekbench OpenCL?

A: The NVIDIA GeForce RTX 3080 Ti Mobile is significantly faster, scoring 117,866 compared to the AMD Radeon 860M’s 22,759, a delta of -80.7% for the AMD part.

Q: What is the memory bandwidth of each GPU?

A: The NVIDIA GeForce RTX 3080 Ti Mobile has 512.0 GB/s bandwidth from 16 GB of GDDR6 on a 256-bit bus. The AMD Radeon 860M uses System Shared memory with System Dependent bandwidth.

Q: Do both GPUs support ray tracing?

A: Yes, both support DirectX 12 Ultimate (12_2), which includes ray tracing. However, the NVIDIA part has 58 RT cores, while the AMD part has 8.

Q: What is the TDP difference?

A: The AMD Radeon 860M is rated at 15 W, while the NVIDIA GeForce RTX 3080 Ti Mobile is rated at 115 W. This is a 100 W difference.

Q: Which GPU has a higher average benchmark score?

A: The AMD Radeon 860M has a slightly higher average score of 26,401 versus 25,740 for the NVIDIA part, but this is based on different test suites.

Q: What is the process node for each chip?

A: The AMD Radeon 860M uses a 4 nm TSMC process, while the NVIDIA GeForce RTX 3080 Ti Mobile uses an 8 nm Samsung process.

Specification Differences

The following fields differ between the two GPUs, based solely on the FACT PACK:

• Process Node: AMD Radeon 860M is 4 nm; NVIDIA RTX 3080 Ti Mobile is 8 nm.
• Foundry: AMD uses TSMC; NVIDIA uses Samsung.
• Transistors: NVIDIA has 22,000 million; AMD is unknown.
• Die Size: NVIDIA is 496 mm²; AMD is unknown.
• Transistor Density: NVIDIA is 44.4M / mm²; AMD is null.
• Base Clock: AMD is 600 MHz; NVIDIA is 810 MHz.
• Boost Clock: AMD is 3000 MHz; NVIDIA is 1260 MHz.
• Memory Size: AMD is System Shared; NVIDIA is 16 GB.
• Memory Type: AMD is System Shared; NVIDIA is GDDR6.
• Memory Bus Width: AMD is System Shared; NVIDIA is 256 bit.
• Memory Bandwidth: AMD is System Dependent; NVIDIA is 512.0 GB/s.
• Shading Units: AMD has 512; NVIDIA has 7,424.
• TMUs: AMD has 32; NVIDIA has 232.
• ROPs: AMD has 16; NVIDIA has 96.
• RT Cores: AMD has 8; NVIDIA has 58.
• Tensor Cores: AMD has none; NVIDIA has 232.
• Pixel Rate: AMD is 48.00 GPixel/s; NVIDIA is 121.0 GPixel/s.
• Texture Rate: AMD is 96.00 GTexel/s; NVIDIA is 292.3 GTexel/s.
• FP32: AMD is 3.072 TFLOPS; NVIDIA is 18.71 TFLOPS.
• FP16: AMD is 3.072 TFLOPS; NVIDIA is 18.71 TFLOPS.
• TDP: AMD is 15 W; NVIDIA is 115 W.
• Bus Interface: AMD is PCIe 4.0 x8; NVIDIA is PCIe 4.0 x16.
• Production Status: AMD is Active; NVIDIA is End-of-life.
• Release Date: AMD is 2025-02-28; NVIDIA is 2022-01-24.
• Predecessor: AMD is Navi II IGP; NVIDIA is GeForce 20 Mobile.
• Series: AMD has none; NVIDIA is GeForce 30-series.
• Generation: AMD is Navi III IGP (Strix Point Mobile); NVIDIA is GeForce 30 Mobile.
• Chip: AMD is Krackan Point; NVIDIA is GA103.
• Architecture: AMD is RDNA 3.5; NVIDIA is Ampere.
• Slot Width: AMD is IGP; NVIDIA is null.

The Verdict

The GeForce RTX 3080 Ti Mobile is the superior performer by a wide margin. In the only shared tests, it leads by 80.7% in OpenCL and 72.1% in Vulkan. Its 18.71 TFLOPS FP32 compute dwarfs the Radeon 860M’s 3.072 TFLOPS, and its 512.0 GB/s memory bandwidth is a necessity for modern gaming. This is a discrete GPU designed for high-end laptops, and the data confirms it delivers.

The AMD Radeon 860M is not without merit. It is an integrated solution with a 15 W TDP, making it suitable for ultraportable devices. Its 4 nm process is state-of-the-art, and its average benchmark score of 26,401 places it near the NVIDIA GeForce MX550, a discrete entry-level part. For users who need basic GPU acceleration without a dedicated card, it is a sound choice.

The verdict is clear: choose the RTX 3080 Ti Mobile if you require maximum performance for gaming, rendering, or compute tasks. Choose the Radeon 860M if you prioritize efficiency and integration in a thin-and-light chassis. The data shows no overlap in performance tiers; the only shared benchmarks are decisive wins for NVIDIA. The RTX 3080 Ti Mobile’s End-of-life status does not diminish its capability, while the Radeon 860M’s Active status suggests it will remain relevant in new systems. For raw speed, the NVIDIA part wins outright.