NVIDIA GeForce GTX 670M vs NVIDIA GeForce MX130 Comparison

The NVIDIA GeForce GTX 670M and the NVIDIA GeForce MX130 represent two distinct eras of mobile graphics, separated by roughly five years of architectural evolution. The recorded benchmark data shows the GTX 670M winning the only shared head-to-head test, the Geekbench OpenCL workload, with a score of 6513 against the MX130's 6102. That is a 6.7% advantage for the older card, a result that challenges the assumption that newer always means faster. However, the MX130 counters with a lower power draw, a more modern feature set, and a smaller physical footprint, making the choice between them heavily dependent on the intended use case.

Head-to-Head Benchmarks

The single direct comparison available in the database is the Geekbench OpenCL test. The GTX 670M scores 6513, while the MX130 scores 6102. The delta is 6.7% in favor of the GTX 670M. In practical terms, this means the older Fermi-based chip delivers roughly seven percent more compute throughput in this particular OpenCL workload. The margin is not overwhelming, but it is consistent and measurable.

Looking at the broader context, the GTX 670M's average benchmark score of 6513 places it at the 38th percentile among all GPUs in the database. Its nearest rivals include the NVIDIA GeForce GT 555M at 6493 (0.3% slower), the NVIDIA Quadro M5000M at 6481 (0.5% slower), and the AMD Radeon Vega 10 Mobile at 6476 (0.6% slower). The Intel UHD Graphics P750 sits slightly ahead at 6554, a 0.6% margin over the GTX 670M. These figures indicate that the GTX 670M sits in a tightly packed cluster of mid-range mobile parts, where a few percentage points separate entire tiers of performance.

The MX130, by contrast, has an average benchmark score of 5508, which places it at the 32nd percentile. That is a six-percentile gap to the GTX 670M, and the average score difference is substantial: 6513 versus 5508, a difference of 1005 points, or roughly 18.2% lower. However, the MX130's nearest rivals tell a slightly different story. The NVIDIA GeForce GTX 765M scores 5501 (0.1% slower), the AMD Radeon R7 M440 scores 5483 (0.5% slower), and the NVIDIA Quadro M4000 scores 5467 (0.7% slower). The AMD FirePro M4000 is marginally ahead at 5537, a 0.5% edge. This suggests the MX130 is competitive within its own tier, even though that tier sits below the GTX 670M's.

The MX130 also has a Vulkan score of 4914, a test the GTX 670M does not have recorded. Vulkan support is a meaningful differentiator for newer applications, but without a comparable GTX 670M score, the database cannot confirm which card handles Vulkan workloads better. The OpenCL result remains the only apples-to-apples comparison, and it favors the GTX 670M.

Architecture Differences

The architectural gap between these two cards is wide. The GTX 670M uses the GF114 chip based on Fermi 2.0 architecture, built on a 40 nm process at TSMC. The chip contains 1,950 million transistors on a die size of 332 mm², yielding a transistor density of 5.9 million per square millimeter. The MX130 uses the GM108S chip based on Maxwell architecture, also fabricated by TSMC but on a 28 nm process. It packs 1,020 million transistors into just 77 mm², giving it a transistor density of 13.2 million per square millimeter, more than double the GTX 670M's density.

The memory subsystems diverge sharply. The GTX 670M comes with 1536 MB of GDDR5 on a 192-bit bus, producing a bandwidth of 72.00 GB/s. The MX130 offers 2 GB of GDDR5, but on a narrow 64-bit bus, capping bandwidth at 40.10 GB/s. The GTX 670M's wider bus gives it a 79.6% bandwidth advantage, even though the MX130 has more total memory. The MX130's memory clock is listed at 1253 MHz with 5 Gbps effective, while the GTX 670M's memory runs at 750 MHz with 3 Gbps effective. The MX130's faster memory clock cannot compensate for the much narrower bus.

Compute resources also differ. The GTX 670M has 336 shading units, 56 texture mapping units, and 24 raster output units. The MX130 has 384 shading units, but only 24 TMUs and 8 ROPs. The shading unit count favors the MX130, but the GTX 670M has more than double the TMUs and triple the ROPs. This reflects different design priorities: the GTX 670M was built for sustained rendering throughput, while the MX130 focuses on efficiency and lighter workloads.

Pixel and texture rates confirm this. The GTX 670M achieves 8.372 GPixel/s and 33.49 GTexel/s. The MX130 reaches 9.512 GPixel/s and 28.54 GTexel/s. The MX130 wins pixel throughput by 13.6%, but the GTX 670M wins texture throughput by 17.3%. FP32 compute is closer: the GTX 670M delivers 803.7 GFLOPS, while the MX130 delivers 913.2 GFLOPS, a 13.6% advantage for the newer chip.

Power consumption is a major differentiator. The GTX 670M has a TDP of 75 W and uses an MXM module form factor with an MXM-B (3.0) bus interface. The MX130 has a TDP of just 30 W and is an integrated graphics processor (IGP) with a PCIe 3.0 x4 interface. That is a 60% reduction in power draw for the MX130, which makes it suitable for thin-and-light laptops where the GTX 670M's MXM module would not fit or would require significantly more cooling.

API support also diverges. Both cards support DirectX 12 (11_0) and OpenGL 4.6. The MX130 additionally supports Vulkan 1.4, while the GTX 670M has no recorded Vulkan support. This is a real advantage for the MX130 in modern titles that leverage Vulkan for lower overhead and better multi-threading.

The Verdict

The data points to a clear split. For raw compute performance in the recorded OpenCL test, the GTX 670M is the winner, scoring 6.7% higher than the MX130 and sitting at a higher percentile rank (38th versus 32nd). The GTX 670M also offers significantly higher memory bandwidth (72.00 GB/s versus 40.10 GB/s) and more texture units and ROPs, which historically translates to better sustained performance in texture-heavy and raster-bound workloads.

The MX130, however, wins on efficiency and portability. Its 30 W TDP is 45 W lower than the GTX 670M's 75 W, making it far better suited for laptops that prioritize battery life and slim profiles. It also has more shading units (384 versus 336), higher FP32 compute (913.2 GFLOPS versus 803.7 GFLOPS), and Vulkan support, which the GTX 670M lacks. The MX130's 2 GB memory capacity is also larger than the GTX 670M's 1536 MB, which can matter for modern applications that require more framebuffer.

The GTX 670M is an end-of-life product from 2012, and the MX130 is an end-of-life product from 2017. Neither is current, but the MX130's newer architecture gives it features that the GTX 670M cannot match. The GTX 670M's advantage in the head-to-head benchmark is real, but it comes at the cost of more power, a larger physical footprint, and no Vulkan support.

Users who need maximum performance in OpenCL-based workloads, or who value memory bandwidth and texture throughput, should look at the GTX 670M. Users who need a low-power, compact solution with modern API support and higher FP32 compute should pick the MX130.

FAQ

Q: Which GPU is faster in the Geekbench OpenCL test?

A: The NVIDIA GeForce GTX 670M scores 6513, while the NVIDIA GeForce MX130 scores 6102. The GTX 670M wins by 6.7%.

Q: How much memory bandwidth does each card have?

A: The GTX 670M has 72.00 GB/s of bandwidth from a 192-bit bus, while the MX130 has 40.10 GB/s from a 64-bit bus.

Q: Does the MX130 support Vulkan?

A: Yes, the MX130 supports Vulkan 1.4. The GTX 670M has no recorded Vulkan support in the database.

Q: What are the TDP ratings for both cards?

A: The GTX 670M has a TDP of 75 W, while the MX130 has a TDP of 30 W.

Q: Which GPU has more shading units?

A: The MX130 has 384 shading units, compared to 336 on the GTX 670M.

Q: What is the transistor density difference?

A: The MX130 has a transistor density of 13.2M per mm², while the GTX 670M has 5.9M per mm², based on a 28 nm versus 40 nm process.

Where Each One Wins

The GTX 670M wins in scenarios that demand high memory bandwidth. Its 72.00 GB/s throughput is nearly double the MX130's 40.10 GB/s, which benefits applications that stream large textures or work with high-resolution framebuffers. The GTX 670M also has 56 texture mapping units versus 24 on the MX130, and 24 ROPs versus 8, giving it an edge in fill-rate-bound tasks. Its texture rate of 33.49 GTexel/s is 17.3% higher than the MX130's 28.54 GTexel/s. The GTX 670M's OpenCL score of 6513 also places it at the 38th percentile, ahead of the MX130's 32nd percentile, making it the better choice for compute-heavy applications that rely on OpenCL.

The MX130 wins in efficiency and modern feature support. Its 30 W TDP makes it suitable for laptops where the 75 W GTX 670M would be impractical. The MX130's FP32 compute of 913.2 GFLOPS is 13.6% higher than the GTX 670M's 803.7 GFLOPS, which can translate to better performance in shader-bound workloads that use the GPU's compute units directly. The MX130's 384 shading units outnumber the GTX 670M's 336, providing more parallel execution lanes for certain tasks. Its Vulkan 1.4 support opens the door to modern game engines and applications that use Vulkan, something the GTX 670M cannot offer. The MX130 also has a higher pixel rate of 9.512 GPixel/s versus 8.372 GPixel/s, giving it a 13.6% advantage in pure pixel output.

The MX130's 2 GB memory capacity is 33% larger than the GTX 670M's 1536 MB, which can be a deciding factor for applications that exceed the older card's framebuffer. Its 28 nm process and 13.2M transistors per mm² density indicate a more efficient design, and its PCIe 3.0 x4 interface is more modern than the MXM-B (3.0) bus on the GTX 670M.

For gaming, the GTX 670M's higher bandwidth and texture throughput likely help in traditional rasterized titles, while the MX130's Vulkan support and higher shading unit count may help in newer titles that use that API. The database records only one shared benchmark, so these are inferences from the architectural data rather than direct measurements. The GTX 670M is the stronger choice for raw performance in the recorded test, but the MX130 is the more versatile, efficient, and modern option for portable systems.