AMD Radeon HD 8730M vs NVIDIA GeForce GTX 460 SE Comparison

Where Each One Wins

The benchmark data splits cleanly along generational and architectural lines. The NVIDIA GeForce GTX 460 SE wins the only recorded head-to-head comparison, the Geekbench OpenCL test, by a margin of 7.3%. That single victory places it in the 37th percentile of all GPUs in the database. The AMD Radeon HD 8730M, by contrast, sits in the 34th percentile. The GTX 460 SE is the stronger compute performer in this pairing, delivering a raw OpenCL score of 6389 against 5955 for the HD 8730M.

The HD 8730M does not win any recorded benchmark category. Its advantage is structural rather than performance based. It is a smaller, more modern chip built on a 28 nm process, versus the 40 nm process of the GTX 460 SE. That gives it a substantially higher transistor density, 12.3M per square millimeter versus 5.9M for the older NVIDIA part. In practical terms, the HD 8730M is the more efficient design per unit of silicon area, while the GTX 460 SE is the outright compute winner.

Use-case separation follows from these facts. The GTX 460 SE is the pick for OpenCL compute workloads where raw score matters. The HD 8730M is the pick for systems where power draw, physical footprint, and memory capacity take priority. The HD 8730M carries 2 GB of DDR3 memory, double the 1 GB GDDR5 of the GTX 460 SE, though that memory runs at a far lower bandwidth. The GTX 460 SE is a dual-slot desktop card with two 6-pin power connectors and a 450 W suggested PSU. The HD 8730M has no recorded slot width, power connector, or PSU requirement, consistent with a mobile-oriented part.

Architecture Differences

The two GPUs come from different architectural lineages entirely. The GTX 460 SE uses the GF104 chip, built on NVIDIA's Fermi architecture, and belongs to the GeForce 400 generation. It is manufactured on a 40 nm process at TSMC, with 1,950 million transistors on a 332 mm² die. The HD 8730M uses the Mars chip, built on AMD's GCN 1.0 architecture, and belongs to the Solar System (HD 8700M) generation. It is also a TSMC product, but on a 28 nm process, packing 950 million transistors into a 77 mm² die.

The transistor figures tell a clear story. The GTX 460 SE has more than twice the transistor count of the HD 8730M, 1,950 million versus 950 million, and a die over four times larger at 332 mm² versus 77 mm². The HD 8730M counters with a transistor density of 12.3M per square millimeter, more than double the 5.9M of the GTX 460 SE. That density advantage is the direct result of the newer 28 nm node.

Shading unit counts also differ. The HD 8730M has 384 shading units, while the GTX 460 SE has 288. The GTX 460 SE compensates with 48 texture mapping units and 32 ROPs, against 24 TMUs and 8 ROPs for the AMD part. The GTX 460 SE also holds the memory interface edge with a 256 bit bus, versus 128 bit on the HD 8730M. Memory type differs as well: GDDR5 on the NVIDIA card, DDR3 on the AMD card. The GTX 460 SE memory runs at 850 MHz with 3.4 Gbps effective data rate, while the HD 8730M memory runs at 900 MHz with 1800 Mbps effective.

API support shows a generational gap. Both support DirectX 12 and OpenGL 4.6, but the HD 8730M lists Vulkan 1.2.170 support, while the GTX 460 SE has no recorded Vulkan capability. The HD 8730M DirectX level is 12 (11_1), slightly higher than the 12 (11_0) of the GTX 460 SE.

Head-to-Head Benchmarks

The only recorded benchmark, Geekbench OpenCL, favors the GTX 460 SE with a score of 6389 against 5955 for the HD 8730M, a delta of 7.3%. That is a meaningful but not overwhelming margin. The GTX 460 SE sits at the 37th percentile of all GPUs, while the HD 8730M sits at the 34th percentile. A three percentile gap matches the 7.3% score difference.

The nearest rival data provides additional context. The GTX 460 SE at 6389 is exactly matched by the NVIDIA GeForce GTX 580M, which also scores 6389 for a delta of 0%. It trails the NVIDIA RTX PRO 5000 72 GB Blackwell by 0.3%, which scores 6407. It leads the AMD Radeon Pro WX 4100 by 0.9% (6330) and the AMD Radeon R7 M350 by 1% (6327). The GTX 460 SE is thus clustered in a tight band where a few points separate it from four other GPUs.

The HD 8730M at 5955 sits in a similarly tight cluster. It is effectively tied with the NVIDIA Quadro K620M, which scores 5957 for a delta of 0%. It trails the AMD Radeon HD 8750M by 0.3% (5970) and the NVIDIA Quadro K4000 by 0.5% (5982). It leads the Intel UHD Graphics 730 by 0.4% (5929). The HD 8730M is therefore within 1% of four other GPUs, none of which are the GTX 460 SE.

Pixel and texture rates reinforce the GTX 460 SE advantage. The NVIDIA card outputs 7.800 GPixel/s and 31.20 GTexel/s. The AMD card outputs 5.600 GPixel/s and 16.80 GTexel/s. That is 39% higher pixel throughput and 86% higher texture throughput for the GTX 460 SE, though those specific percentage comparisons are derived from the recorded rates. FP32 compute also favors NVIDIA: 748.8 GFLOPS versus 537.6 GFLOPS.

Specification Differences

The two cards differ on nearly every measurable specification. Process node: 40 nm for the GTX 460 SE, 28 nm for the HD 8730M. Transistors: 1,950 million versus 950 million. Die size: 332 mm² versus 77 mm². Transistor density: 5.9M per mm² versus 12.3M per mm².

Memory configuration diverges sharply. The GTX 460 SE has 1024 MB of GDDR5 on a 256 bit bus with 108.8 GB/s bandwidth. The HD 8730M has 2 GB of DDR3 on a 128 bit bus with 28.80 GB/s bandwidth. The GTX 460 SE has nearly four times the memory bandwidth, while the HD 8730M has double the capacity.

Compute resources differ in both count and balance. The GTX 460 SE has 288 shading units, 48 TMUs, and 32 ROPs. The HD 8730M has 384 shading units, 24 TMUs, and 8 ROPs. The HD 8730M has more shading units but far fewer texture and pixel units. Rated throughput follows: 7.800 GPixel/s and 31.20 GTexel/s for NVIDIA, 5.600 GPixel/s and 16.80 GTexel/s for AMD. FP32 is 748.8 GFLOPS versus 537.6 GFLOPS.

Clock behavior differs. The HD 8730M has a recorded base clock of 650 MHz and boost clock of 700 MHz. The GTX 460 SE has no base or boost clock recorded, only a memory clock of 850 MHz with 3.4 Gbps effective. The HD 8730M memory clock is 900 MHz with 1800 Mbps effective.

Form factor and power delivery are only recorded for the GTX 460 SE. It is a dual-slot card, 210 mm or 8.3 inches long, with 2x 6-pin power connectors and a 450 W suggested PSU. Its TDP is 150 W. The HD 8730M has no TDP, slot width, power connector, PSU, or dimension data recorded. Bus interface: PCIe 2.0 x16 for NVIDIA, PCIe 3.0 x8 for AMD. Display outputs: 2x DVI and 1x mini-HDMI 1.3a for NVIDIA, none recorded for AMD.

Release timing separates them by over two years. The GTX 460 SE launched on 2010-11-14 with a launch MSRP of 160 USD. The HD 8730M launched on 2013-03-31 with no recorded MSRP. Both are end-of-life. Predecessor and successor lines differ: GeForce 200 to GeForce 500 for NVIDIA, London to Gem System for AMD.

FAQ

Q: Which GPU has the higher OpenCL benchmark score?

A: The NVIDIA GeForce GTX 460 SE scores 6389 in Geekbench OpenCL, while the AMD Radeon HD 8730M scores 5955. The GTX 460 SE leads by 7.3%.

Q: How do the memory systems compare?

A: The GTX 460 SE has 1024 MB of GDDR5 on a 256 bit bus with 108.8 GB/s bandwidth. The HD 8730M has 2 GB of DDR3 on a 128 bit bus with 28.80 GB/s bandwidth. The GTX 460 SE has far higher bandwidth, the HD 8730M has double the capacity.

Q: Which GPU is built on a more advanced manufacturing process?

A: The AMD Radeon HD 8730M uses a 28 nm process at TSMC, while the NVIDIA GeForce GTX 460 SE uses a 40 nm process at the same foundry. The HD 8730M also has a higher transistor density at 12.3M per square millimeter versus 5.9M.

Q: What are the pixel and texture rate differences?

A: The GTX 460 SE outputs 7.800 GPixel/s and 31.20 GTexel/s. The HD 8730M outputs 5.600 GPixel/s and 16.80 GTexel/s. The NVIDIA card is higher in both categories.

Q: Does the HD 8730M support Vulkan?

A: Yes, the HD 8730M lists Vulkan 1.2.170 support. The GTX 460 SE has no recorded Vulkan support, though both support DirectX 12 and OpenGL 4.6.

Q: How does the GTX 460 SE compare to its closest rivals?

A: It is exactly tied with the NVIDIA GeForce GTX 580M at a delta of 0%, trails the NVIDIA RTX PRO 5000 72 GB Blackwell by 0.3%, and leads the AMD Radeon Pro WX 4100 by 0.9% and the AMD Radeon R7 M350 by 1%.