NVIDIA GeForce GTX 460 v2 vs NVIDIA GeForce GTX 675MX Comparison

# NVIDIA GeForce GTX 460 v2 vs NVIDIA GeForce GTX 675MX

The NVIDIA GeForce GTX 460 v2 and NVIDIA GeForce GTX 675MX represent two distinct generations of NVIDIA mobile and desktop graphics, separated by a full architecture shift. The GTX 460 v2, built on Fermi 2.0 with a 40 nm process, is a desktop card from the GeForce 400 series, while the GTX 675MX, using Kepler on 28 nm, is a mobile MXM module from the GeForce 600M series. In the single available head-to-head benchmark, the GTX 675MX delivers a decisive victory in OpenCL compute, posting 10,723 points against 8,743 for the GTX 460 v2, a difference of 18.5%. However, the two cards occupy neighboring positions in the overall GPU percentile rankings, with the GTX 460 v2 at the 44th percentile and the GTX 675MX at the 43rd percentile, indicating that their real-world performance envelopes are closer than the raw benchmark delta suggests.

Where Each One Wins

The GTX 675MX wins the only direct benchmark comparison available, the Geekbench OpenCL test, with a score of 10,723 versus 8,743 for the GTX 460 v2. This 18.5% advantage places the Kepler-based mobile part clearly ahead in raw compute workloads that scale with shader count and memory bandwidth. The GTX 675MX also brings a Vulkan API capability (1.2.175) that the GTX 460 v2 lacks entirely, making it the more future-proof option for applications that leverage Vulkan for cross-platform graphics and compute.

The GTX 460 v2, despite losing the head-to-head, has its own strengths. It is a dual-slot desktop card with a 210 mm length, designed for traditional PCIe 2.0 x16 slots, whereas the GTX 675MX is an MXM-B 3.0 module with no fixed dimensions and portable-device-dependent outputs. For users building or upgrading a desktop system, the GTX 460 v2 offers a straightforward installation path with 2x DVI and 1x mini-HDMI 1.3a outputs, while the GTX 675MX requires a compatible laptop or MXM chassis. The GTX 460 v2 also carries a higher TDP of 160 W compared to 100 W for the GTX 675MX, but the desktop card compensates with a 450 W suggested PSU and dual 6-pin power connectors, whereas the mobile part draws power through its MXM interface with no external connectors.

In terms of benchmark positioning relative to their respective nearest rivals, the GTX 460 v2 sits within 1.4% of the AMD Radeon Pro WX 5100 (8,863) and 1.2% below the AMD Radeon R9 M265X (8,851), while the GTX 675MX is within 0.4% of both the NVIDIA GeForce MX330 (8,458) and AMD Radeon HD 8870M (8,462). This suggests that the GTX 675MX competes in a slightly lower performance tier than the GTX 460 v2, despite the latter's lower raw score in the direct comparison.

Architecture Differences

The architectural gap between these two GPUs is substantial. The GTX 460 v2 uses the GF114 chip on a 40 nm TSMC process, packing 1,950 million transistors into a 332 mm² die, yielding a transistor density of 5.9 million per square millimeter. The GTX 675MX uses the GK104 chip on a 28 nm TSMC process, with 3,540 million transistors in a smaller 294 mm² die, achieving a much higher density of 12.0 million per square millimeter. This process shrink allows the Kepler part to nearly double the transistor count while reducing die size by roughly 11%.

The shader configuration differs dramatically. The GTX 460 v2 has 336 shading units, 56 texture mapping units, and 24 ROPs. The GTX 675MX more than doubles the shading units to 960, increases TMUs to 80, and raises ROPs to 32. This translates into higher theoretical throughput across the board: the GTX 675MX delivers 1,255.7 GFLOPS of FP32 compute versus 1,046.3 GFLOPS for the GTX 460 v2, a 20% advantage. Pixel fill rate jumps from 10.91 GPixel/s to 13.08 GPixel/s, and texture fill rate from 43.62 GTexel/s to 52.32 GTexel/s.

Memory subsystems also differ. The GTX 460 v2 has 1,024 MB of GDDR5 on a 192-bit bus, with memory clocked at 1,002 MHz (4 Gbps effective) and bandwidth of 96.19 GB/s. The GTX 675MX doubles capacity to 2 GB on a 256-bit bus, but runs memory at a lower 900 MHz (3.6 Gbps effective), achieving higher total bandwidth of 115.2 GB/s. The combination of more memory, wider bus, and higher aggregate bandwidth favors the GTX 675MX in texture-heavy and high-resolution workloads.

Both cards support DirectX 12 (11_0) and OpenGL 4.6, but the GTX 675MX adds Vulkan 1.2.175 support, which the GTX 460 v2 does not list. The GTX 460 v2 uses PCIe 2.0 x16, while the GTX 675MX uses MXM-B 3.0, reflecting their different intended platforms. The GTX 460 v2 was released on 2011-09-23, while the GTX 675MX followed on 2012-09-30, exactly one year later. Both are now end-of-life products, with the GTX 460 v2 succeeding the GeForce 200 series and preceding the GeForce 500 series, while the GTX 675MX succeeds the GeForce 500M and precedes the GeForce 700M.

Head-to-Head Benchmarks

The only direct benchmark comparison is Geekbench OpenCL, where the GTX 675MX scores 10,723 against the GTX 460 v2's 8,743, a delta of -18.5% from the perspective of the GTX 460 v2. This single data point shows the GTX 675MX outperforming the older desktop card by nearly one-fifth in a compute-heavy workload. The margin is consistent with the raw specification advantages: the GTX 675MX has 2.86 times the shading units, 1.43 times the TMUs, 1.33 times the ROPs, and 19.8% higher FP32 throughput. The bandwidth advantage of 19.8% (115.2 GB/s vs 96.19 GB/s) aligns closely with the compute advantage, suggesting that memory bandwidth is not a bottleneck in this particular test.

However, the head-to-head result does not tell the full story. The GTX 460 v2's average benchmark score across all tests is 8,743, which matches its OpenCL score. The GTX 675MX has two benchmark entries: a Geekbench Metal score of 6,131 and the OpenCL score of 10,723, giving an average of 8,427. This means that while the GTX 675MX wins decisively in OpenCL, its Metal performance is substantially lower, dragging its average below that of the GTX 460 v2. The GTX 460 v2's percentile rank of 44 is slightly higher than the GTX 675MX's 43, indicating that across the broader GPU landscape, the desktop card holds a marginal edge in overall standing.

The nearest rival data reinforces this nuance. The GTX 460 v2's closest competitor is the NVIDIA GeForce RTX 3050 A Mobile with an average score of 8,746, a delta of 0%, followed by the Quadro P2200 at 8,686 (0.7% slower). The GTX 675MX's nearest rival is the AMD Radeon 880M at 8,436 (-0.1%), with the MX330 at 8,458 (-0.4%) close behind. The GTX 460 v2 competes with slightly faster cards (all within 1.4% of its score), while the GTX 675MX's rivals are slightly slower on average (down to 1.2% below), suggesting the GTX 460 v2 holds its own in a slightly higher performance bracket.

FAQ

Q: Which GPU has higher raw compute performance?

A: The GTX 675MX leads in FP32 throughput with 1,255.7 GFLOPS versus 1,046.3 GFLOPS for the GTX 460 v2, a 20% advantage. This is reflected in the OpenCL benchmark where the GTX 675MX scores 10,723 against 8,743.

Q: Do both cards support the same graphics APIs?

A: Both support DirectX 12 (11_0) and OpenGL 4.6, but they differ on Vulkan. The GTX 675MX supports Vulkan 1.2.175, while the GTX 460 v2 has no Vulkan support listed.

Q: How do their memory configurations compare?

A: The GTX 460 v2 has 1,024 MB of GDDR5 on a 192-bit bus with 96.19 GB/s bandwidth. The GTX 675MX has 2 GB of GDDR5 on a 256-bit bus with 115.2 GB/s bandwidth, offering both more capacity and higher bandwidth.

Q: Which card is more power-efficient?

A: The GTX 675MX has a TDP of 100 W versus 160 W for the GTX 460 v2, making the Kepler mobile part 60 W lower in power draw while delivering higher performance.

Q: What are the physical form factor differences?

A: The GTX 460 v2 is a dual-slot desktop card measuring 210 mm (8.3 inches) with 2x DVI and mini-HDMI outputs. The GTX 675MX is an MXM-B 3.0 module with no listed dimensions and portable-device-dependent outputs.

Q: How do the two cards rank against all GPUs?

A: The GTX 460 v2 sits at the 44th percentile, while the GTX 675MX is at the 43rd percentile, indicating near-identical overall standing despite the GTX 675MX's higher peak compute score.

The Verdict

The data supports a clear split based on platform and workload priorities. For compute-heavy workloads, particularly those using OpenCL, the GTX 675MX is the superior choice, delivering 18.5% higher performance in the direct head-to-head test. Its 960 shading units, 2 GB memory, and 115.2 GB/s bandwidth make it better suited for GPU-accelerated tasks and modern API support via Vulkan. The 100 W TDP also makes it the more power-efficient option, a meaningful consideration for mobile or thermally constrained systems.

However, the GTX 460 v2's slightly higher percentile ranking (44 vs 43) and its higher average benchmark score (8,743 vs 8,427) indicate that it holds a small edge in overall versatility. Its desktop form factor with standard display outputs (2x DVI, mini-HDMI) makes it easier to deploy in conventional systems, and its 450 W suggested PSU requirement is modest for a desktop GPU. For users with an existing PCIe 2.0 x16 slot, the GTX 460 v2 offers a straightforward upgrade path without needing a specialized MXM chassis.

The GTX 675MX's Metal score of 6,131 versus its OpenCL score of 10,723 reveals significant API-dependent variance, suggesting that its performance is not uniform across all compute frameworks. Users targeting Metal-based applications would find the GTX 460 v2's consistent OpenCL-only profile less variable, albeit at a lower peak. The GTX 460 v2's launch MSRP of 199 USD also positions it as a fixed-cost desktop option, though the GTX 675MX has no listed MSRP given its mobile OEM nature.

In practical terms, the GTX 675MX wins for laptop users needing the best possible OpenCL compute performance in a 100 W envelope, while the GTX 460 v2 remains a viable desktop part for those prioritizing ease of installation and a slightly better overall GPU percentile standing. The architecture gap — Fermi 2.0 at 40 nm versus Kepler at 28 nm — favors the newer design in raw throughput, but the GTX 460 v2's density of 5.9M transistors per mm² versus 12.0M for the GTX 675MX shows how process technology drove the performance leap. Neither card is competitive in the modern GPU landscape, but for legacy applications and systems, the GTX 675MX offers higher peak compute at lower power, making it the technically stronger part.