AMD Radeon 680M vs NVIDIA GeForce RTX 3060 Mobile Comparison
AMD Radeon 680M
GeForce RTX 3060 Mobile
PERFORMANCE BENCHMARKS
Analysis: AMD Radeon 680M vs NVIDIA GeForce RTX 3060 Mobile
The NVIDIA GeForce RTX 3060 Mobile is the decisive winner in this comparison, taking all three shared benchmark tests with margins that range from roughly 239% to 382%. The AMD Radeon 680M, an integrated graphics processor, is a competent solution for its class, but the data shows it is not in the same performance tier as the discrete RTX 3060 Mobile. For users who need maximum graphics throughput, the NVIDIA part is the clear choice. For those constrained by power limits or who require an integrated solution, the Radeon 680M offers a viable alternative, albeit with substantially lower raw performance.
The Verdict
The benchmark data is unambiguous. In the 3DMark Steel Nomad DX12 test, the RTX 3060 Mobile scores 1821 against the Radeon 680M's 378, a difference of 381.7%. In Geekbench OpenCL, the NVIDIA part scores 79483 versus 23468, a 238.7% lead. In Geekbench Vulkan, it scores 80344 versus 21965, a 265.8% advantage. If the workload is any of these three tests, the RTX 3060 Mobile wins by a wide margin.
The RTX 3060 Mobile also holds a higher position in the overall database. It sits in the 62nd percentile of all GPUs, with an average benchmark score of 18159. The Radeon 680M sits in the 57th percentile, with an average score of 15270. That percentile gap, while smaller than the head-to-head deltas, still places the NVIDIA part ahead in the aggregate ranking.
The Radeon 680M is not without merit. Its nearest rivals in the database include the NVIDIA GeForce GTX 580 (average score 15283, delta -0.1%), the NVIDIA GeForce RTX 2060 (15290, -0.1%), the RTX 3050 OEM (15199, 0.5%), and the AMD Radeon RX 7600 (15171, 0.7%). These deltas are all within 1% of the 680M, meaning it performs in line with those older or lower-tier discrete parts. That is an impressive result for an integrated GPU, but it does not approach the RTX 3060 Mobile, whose nearest rivals include the AMD Radeon Pro 5700 (18189, -0.2%), RTX 2060 SUPER (18093, 0.4%), Radeon RX 460 (18373, -1.2%), and Intel Arc A770M (18383, -1.2%). The RTX 3060 Mobile is competing with a much higher class of hardware.
Architecture Differences
The two GPUs come from different manufacturers and use different process nodes. The RTX 3060 Mobile is built on NVIDIA's Ampere architecture, using the GA106 chip, fabricated on Samsung's 8 nm process. The Radeon 680M uses AMD's RDNA 2.0 architecture, on the Rembrandt+ chip, fabricated by TSMC on a 6 nm process. The Radeon 680M is an integrated graphics processor (IGP), as noted in its slot width field, while the RTX 3060 Mobile is a discrete mobile GPU.
The transistor counts differ, with the RTX 3060 Mobile at 12,000 million transistors on a 276 mm² die, giving a density of 43.5 million transistors per mm². The Radeon 680M has 13,100 million transistors on a smaller 208 mm² die, yielding a higher density of 63.0 million transistors per mm². The 6 nm process allows AMD to pack more transistors into a smaller area.
Core configurations are vastly different. The RTX 3060 Mobile has 3840 shading units, 120 texture mapping units, and 48 ROPs. The Radeon 680M has 768 shading units, 48 TMUs, and 32 ROPs. The NVIDIA part also has 30 RT cores and 120 tensor cores, while the AMD part has 12 RT cores and no tensor cores listed. These numbers explain the large performance gap in compute-heavy tests.
Memory architecture is another major divider. The RTX 3060 Mobile has 6 GB of dedicated GDDR6 memory on a 192-bit bus, with 336.0 GB/s of bandwidth and a memory clock of 1750 MHz (14 Gbps effective). The Radeon 680M uses system shared memory, with a shared bus width and system-dependent bandwidth. The dedicated memory of the RTX 3060 Mobile provides a significant advantage in bandwidth-sensitive workloads.
Where Each One Wins
The RTX 3060 Mobile wins in every benchmark test where both parts have recorded scores. That includes 3DMark Steel Nomad DX12, Geekbench OpenCL, and Geekbench Vulkan. In the broader database, the RTX 3060 Mobile also has scores in Passmark tests, including DirectX 9 (146), DirectX 10 (90), DirectX 11 (110), DirectX 12 (58), G2D (588), G3D (13230), and GPU compute (5718). The Radeon 680M has no recorded Passmark scores in the database, so no comparison is possible there.
The Radeon 680M wins in the category of efficiency and integration. Its TDP is 50 W, compared to the RTX 3060 Mobile's 80 W. It is an IGP, meaning it requires no separate power connector and is designed to be part of a mobile processor package. The RTX 3060 Mobile also has no power connectors listed, but it is a discrete GPU with a higher power draw. The Radeon 680M's smaller die size and higher transistor density suggest a more integrated design.
In terms of raw performance, the RTX 3060 Mobile is the only choice. The Radeon 680M's nearest rival, the RTX 2060, has an average score of 15290, which is only 0.1% different from the 680M's 15270. That puts the 680M in the range of a previous-generation mid-range discrete GPU. The RTX 3060 Mobile, by contrast, is within 1.2% of the Intel Arc A770M and the AMD Radeon RX 460, which are higher-performing parts.
FAQ
Q: Which GPU has the higher average benchmark score?
A: The NVIDIA GeForce RTX 3060 Mobile has an average benchmark score of 18159, while the AMD Radeon 680M has an average score of 15270.
Q: How large is the performance gap in the 3DMark Steel Nomad DX12 test?
A: The RTX 3060 Mobile scores 1821, and the Radeon 680M scores 378. The RTX 3060 Mobile leads by 381.7%.
Q: Does the Radeon 680M have dedicated video memory?
A: No. The Radeon 680M uses system shared memory, with a system-dependent bandwidth. The RTX 3060 Mobile has 6 GB of GDDR6 memory on a 192-bit bus.
Q: Which GPU has a higher transistor density?
A: The AMD Radeon 680M has a higher transistor density at 63.0 million transistors per mm², compared to the RTX 3060 Mobile's 43.5 million per mm².
Q: What is the power draw difference?
A: The RTX 3060 Mobile has a TDP of 80 W, while the Radeon 680M has a TDP of 50 W.
Q: Which GPU has a higher percentile ranking in the database?
A: The RTX 3060 Mobile is in the 62nd percentile of all GPUs, while the Radeon 680M is in the 57th percentile.
Head-to-Head Benchmarks
The three shared benchmarks all show the same outcome: a dominant win for the RTX 3060 Mobile. The largest margin is in 3DMark Steel Nomad DX12, where the NVIDIA part scores 1821 versus the AMD part's 378. That is a 381.7% difference, meaning the RTX 3060 Mobile delivers nearly five times the score of the Radeon 680M in this test. The Steel Nomad workload is a modern DX12 test, and the gap indicates the RTX 3060 Mobile has substantially more headroom for current-generation gaming and compute loads.
In Geekbench Vulkan, the RTX 3060 Mobile scores 80344, and the Radeon 680M scores 21965. The delta is 265.8%. Vulkan is a cross-platform graphics and compute API, and the RTX 3060 Mobile's advantage here is consistent with its larger shading unit count and dedicated memory. The Radeon 680M's 768 shading units are far fewer than the RTX 3060 Mobile's 3840, and the shared memory subsystem cannot match the bandwidth of 336.0 GB/s GDDR6.
In Geekbench OpenCL, the RTX 3060 Mobile scores 79483, and the Radeon 680M scores 23468, a 238.7% lead. OpenCL is heavily used for general-purpose GPU compute, and the RTX 3060 Mobile's 120 tensor cores and higher FP32 throughput (10.94 TFLOPS versus 3.379 TFLOPS) give it a massive edge in such workloads. The Radeon 680M's FP16 performance of 6.758 TFLOPS is higher than its FP32 rate due to a 2:1 ratio, while the RTX 3060 Mobile runs FP16 at a 1:1 ratio with FP32, but the NVIDIA part's raw FP32 output is still more than three times higher.
The RTX 3060 Mobile also has a higher texture rate at 171.0 GTexel/s, versus the Radeon 680M's 105.6 GTexel/s. The pixel rates are closer, with the RTX 3060 Mobile at 68.40 GPixel/s and the Radeon 680M at 70.40 GPixel/s. That near parity in pixel rate is notable, but it does not offset the massive differences in texture rate, compute throughput, and memory bandwidth.
In the aggregate, the RTX 3060 Mobile's average benchmark score of 18159 places it near the AMD Radeon Pro 5700 (18189, -0.2%) and the RTX 2060 SUPER (18093, 0.4%). The Radeon 680M's average of 15270 places it near the GTX 580 (15283, -0.1%) and the RTX 2060 (15290, -0.1%). The difference between the two GPUs' average scores is roughly 2889 points, a gap that exceeds the entire average score of many low-end parts.
Specification Differences
The two GPUs differ in nearly every major specification. The process node is 8 nm for the RTX 3060 Mobile (Samsung) and 6 nm for the Radeon 680M (TSMC). The die size is 276 mm² for the NVIDIA part and 208 mm² for the AMD part. Transistor counts are 12,000 million for the RTX 3060 Mobile and 13,100 million for the Radeon 680M.
Core counts diverge sharply. The RTX 3060 Mobile has 3840 shading units, 120 TMUs, 48 ROPs, 30 RT cores, and 120 tensor cores. The Radeon 680M has 768 shading units, 48 TMUs, 32 ROPs, and 12 RT cores. The NVIDIA part has no listed tensor core equivalent on the AMD side.
Clock speeds differ as well. The RTX 3060 Mobile has a base clock of 900 MHz and a boost clock of 1425 MHz. The Radeon 680M has a base clock of 2000 MHz and a boost clock of 2200 MHz. Despite the higher clocks, the Radeon 680M cannot match the RTX 3060 Mobile's throughput because of the large difference in core counts.
Memory specifications are fundamentally different. The RTX 3060 Mobile uses 6 GB of GDDR6 on a 192-bit bus with 336.0 GB/s bandwidth. The Radeon 680M uses system shared memory with a system-dependent bandwidth. The memory clock is 1750 MHz (14 Gbps effective) for the NVIDIA part, while the AMD part lists no fixed memory clock.
Compute rates are also different. The RTX 3060 Mobile delivers 10.94 TFLOPS FP32 and 10.94 TFLOPS FP16 (1:1). The Radeon 680M delivers 3.379 TFLOPS FP32 and 6.758 TFLOPS FP16 (2:1). The pixel rate is 68.40 GPixel/s for the NVIDIA part and 70.40 GPixel/s for the AMD part. The texture rate is 171.0 GTexel/s for the RTX 3060 Mobile and 105.6 GTexel/s for the Radeon 680M.
Power and interface also differ. The RTX 3060 Mobile has a TDP of 80 W, while the Radeon 680M has a TDP of 50 W. The bus interface is PCIe 4.0 x16 for the NVIDIA part and PCIe 4.0 x8 for the AMD part. The RTX 3060 Mobile is end-of-life in production status, while the Radeon 680M is active. The RTX 3060 Mobile was released on 2021-01-11, and the Radeon 680M on 2023-01-02. The RTX 3060 Mobile's predecessor is the GeForce 20 Mobile, while the Radeon 680M's predecessor is the Vega II IGP and its successor is the Navi III IGP. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The slot width for the Radeon 680M is listed as IGP, and neither part has a display output specification beyond portable device dependent.