NVIDIA GeForce 930M vs NVIDIA GeForce GTX 460M Comparison

The NVIDIA GeForce 930M and NVIDIA GeForce GTX 460M represent two distinct eras of mobile graphics, separated by roughly five years of architectural evolution. The 930M, built on the Maxwell architecture, faces off against the older Fermi-based GTX 460M. Benchmark data shows the newer part leads in the sole compute test, but the specification sheet tells a more nuanced story of trade-offs between efficiency, memory technology, and raw throughput capabilities.

FAQ

Q: Which GPU is faster in the available benchmark data?

A: The NVIDIA GeForce 930M wins the only head-to-head benchmark available. In Geekbench OpenCL, the 930M scores 5046 against the GTX 460M's 4282, a delta of 17.8% in favor of the newer Maxwell part.

Q: How do these GPUs compare to their nearest rivals?

A: The 930M sits at the 26th percentile of all GPUs with an average benchmark score of 4388, placing it 0.5% behind the GeForce GT 645M and 0.7% ahead of the Intel Iris Pro Graphics 5200. The GTX 460M is at the 25th percentile with a 4282 average, 0.3% behind the AMD FirePro W2100 and 0.3% ahead of the AMD Radeon Vega 3.

Q: What are the memory configurations of these two cards?

A: The 930M comes with 2 GB of DDR3 on a 64-bit bus, yielding 12.80 GB/s of bandwidth. The GTX 460M has 1536 MB of GDDR5 on a 192-bit bus, delivering 60.00 GB/s — nearly five times higher memory bandwidth.

Q: Which GPU has more shading units?

A: The 930M has 384 shading units, exactly double the 192 shading units found in the GTX 460M. However, the GTX 460M counters with more texture mapping units (32 vs 24) and more render output units (24 vs 8).

Q: What is the process node difference between these architectures?

A: The 930M uses a 28 nm process at TSMC, while the GTX 460M uses a larger 40 nm node. This contributes to the 930M's significantly lower 33 W TDP compared to the GTX 460M's 50 W.

Q: Do both GPUs support the same modern APIs?

A: Both support DirectX 12 (11_0) and OpenGL 4.6. The 930M adds Vulkan 1.4 support, while the GTX 460M has no Vulkan support listed.

Architecture Differences

The architectural gap between these two mobile GPUs is substantial, reflecting the generational leap from Fermi to Maxwell. The 930M is built on the GM108S chip using TSMC's 28 nm process, packing 1,020 million transistors into a compact 77 mm² die. This yields a transistor density of 13.2 million transistors per square millimeter. The GTX 460M, in contrast, uses the GF106 chip on a 40 nm process, with 1,170 million transistors spread across a much larger 238 mm² die, resulting in a far lower density of 4.9 million transistors per square millimeter.

The Maxwell architecture in the 930M emphasizes efficiency-per-clock. Its 384 shading units operate at a base and boost clock of 549 MHz, producing 421.6 GFLOPS of FP32 compute. The Fermi-based GTX 460M, despite having only 192 shading units, runs at a higher memory clock and achieves 518.4 GFLOPS of FP32 performance. This is a notable inversion: the older card has higher raw floating-point throughput, yet loses in the OpenCL benchmark.

Memory architecture diverges sharply. The 930M uses 2 GB of DDR3 on a 64-bit bus — a configuration designed for low power consumption rather than peak bandwidth. The GTX 460M uses 1536 MB of GDDR5 on a 192-bit bus, providing 60.00 GB/s of bandwidth versus the 930M's 12.80 GB/s. This 4.7x bandwidth advantage is the GTX 460M's most significant architectural asset.

The pixel and texture throughput also favor the older part. The GTX 460M delivers 5.400 GPixel/s and 21.60 GTexel/s, while the 930M manages 4.392 GPixel/s and 13.18 GTexel/s. The GTX 460M's 24 ROPs versus the 930M's 8 ROPs explains the pixel rate difference, while its 32 TMUs against 24 TMUs drives the texture throughput advantage.

Power and physical design differ as well. The 930M is an IGP (integrated graphics processor) with a 33 W TDP and no power connectors, making it suitable for ultraportable designs. The GTX 460M is an MXM module with a 50 W TDP, also requiring no external power connectors but demanding more thermal headroom. The 930M uses PCIe 3.0 x8, while the GTX 460M uses the older PCIe 2.0 x16 interface.

Head-to-Head Benchmarks

The sole head-to-head benchmark available is Geekbench OpenCL, where the 930M decisively outperforms the GTX 460M. The 930M scores 5046, while the GTX 460M scores 4282, giving the Maxwell part a 17.8% advantage. This result is particularly interesting given the GTX 460M's higher FP32 peak (518.4 GFLOPS vs 421.6 GFLOPS) and vastly superior memory bandwidth (60.00 GB/s vs 12.80 GB/s).

The benchmark outcome suggests that the 930M's newer architecture extracts better real-world compute efficiency from its hardware. Despite having fewer TMUs, fewer ROPs, and slower memory, the 930M's 384 shading units and Maxwell's improved instruction scheduling deliver superior OpenCL performance. The 17.8% delta is substantial in the mobile GPU space, where thermal and power constraints often limit sustained performance.

Average benchmark scores corroborate this result. The 930M's average across its available tests is 4388, while the GTX 460M averages 4282 — a narrower 2.5% gap when including the Vulkan test where the 930M scores 3729. The GTX 460M has no Vulkan score listed, which may reflect its lack of Vulkan API support.

In the context of their nearest rivals, both GPUs occupy similar performance tiers. The 930M's average score of 4388 places it within 2.2% of the AMD FirePro W2100 (4295) and 1.2% of the GeForce RTX 4070 GDDR6 (4335), though the RTX 4070's inclusion in this low-end segment appears anomalous. The GTX 460M's 4282 average sits 1% behind the Quadro K3000M (4241 is lower, so the GTX 460M is actually 1% ahead) and 0.3% behind the FirePro W2100.

Specification Differences

The specification sheets reveal fundamental differences in almost every measurable category. The 930M uses the GM108S chip on a 28 nm process, while the GTX 460M uses the GF106 on 40 nm. Transistor counts are similar (1,020 million vs 1,170 million), but die size differs dramatically: 77 mm² for the 930M versus 238 mm² for the GTX 460M.

Memory configuration is a major differentiator. The 930M has 2 GB of DDR3 on a 64-bit bus with 12.80 GB/s bandwidth and an 800 MHz memory clock (1600 Mbps effective). The GTX 460M has 1536 MB of GDDR5 on a 192-bit bus with 60.00 GB/s bandwidth and a 625 MHz memory clock (2.5 Gbps effective).

Compute resources differ significantly. The 930M has 384 shading units, 24 TMUs, and 8 ROPs. The GTX 460M has 192 shading units, 32 TMUs, and 24 ROPs. This results in different throughput characteristics: the 930M produces 421.6 GFLOPS FP32, 4.392 GPixel/s, and 13.18 GTexel/s, while the GTX 460M produces 518.4 GFLOPS FP32, 5.400 GPixel/s, and 21.60 GTexel/s.

Clock speeds are not directly comparable since the GTX 460M lists no base or boost clock, only its memory clock. The 930M runs at 549 MHz for both base and boost. The GTX 460M's memory clock of 625 MHz is lower in raw frequency but achieves higher effective data rates due to GDDR5's double data rate signaling.

Power and form factor differ markedly. The 930M is an IGP with 33 W TDP, while the GTX 460M is an MXM module with 50 W TDP. Neither requires power connectors. The bus interface also differs: PCIe 3.0 x8 for the 930M versus PCIe 2.0 x16 for the GTX 460M.

API support is nearly identical, with both supporting DirectX 12 (11_0) and OpenGL 4.6. The 930M adds Vulkan 1.4; the GTX 460M has no Vulkan support. Release dates show the 930M launched on 2015-03-12, while the GTX 460M launched on 2010-09-02. The 930M's predecessor is the GeForce 800M and successor is GeForce 10 Mobile; the GTX 460M's predecessor is GeForce 300M and successor is GeForce 500M.

The Verdict

The data presents a clear but qualified picture. The NVIDIA GeForce 930M is the better choice for users prioritizing modern compute performance and efficiency. It wins the OpenCL benchmark by 17.8%, matches the GTX 460M in DirectX and OpenGL API support, adds Vulkan 1.4, and does so at a lower 33 W TDP versus 50 W. Its IGP form factor and PCIe 3.0 x8 interface make it suitable for thinner, lighter laptops.

The GTX 460M, however, retains advantages in memory bandwidth and raw throughput metrics. Its 60.00 GB/s bandwidth is 4.7x higher than the 930M's 12.80 GB/s, and its FP32 peak of 518.4 GFLOPS exceeds the 930M's 421.6 GFLOPS. For workloads that are bandwidth-bound or that leverage the GTX 460M's higher pixel and texture rates (5.400 GPixel/s and 21.60 GTexel/s versus 4.392 and 13.18), the older Fermi part could theoretically perform better, though the OpenCL results suggest otherwise.

The percentile rankings are nearly identical: 26th percentile for the 930M versus 25th for the GTX 460M. Both are end-of-life products with no launch MSRP listed. The 930M has a slightly higher average benchmark score (4388 vs 4282) and more benchmark data points, including a Vulkan score of 3729.

Users should select based on workload. For general compute tasks, modern API support, and power-sensitive designs, the 930M is the data-backed winner. For scenarios requiring maximum memory bandwidth or where the MXM form factor is mandatory, the GTX 460M remains a viable, if older, option. The 17.8% OpenCL delta, however, suggests that most users will find the 930M's real-world performance superior despite the GTX 460M's impressive on-paper throughput numbers.