NVIDIA GeForce 940MX vs NVIDIA Quadro P400 Comparison

The NVIDIA GeForce 940MX and NVIDIA Quadro P400 are both end-of-life, low-profile graphics solutions from different eras of NVIDIA’s lineup. The 940MX, a 2016 Maxwell part, and the P400, a 2017 Pascal workstation card, target very different use cases despite their similar 2 GB memory configurations. Benchmark data shows a split decision: the 940MX wins in OpenCL compute, while the P400 takes the Vulkan crown. This analysis breaks down the architectural, specification, and performance differences to help determine which legacy card suits specific workloads.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce 940MX has a higher average benchmark score of 4844, compared to the Quadro P400’s 4684. The 940MX also sits at the 28th percentile of all GPUs, while the P400 is at the 27th percentile.

Q: How do the two cards compare in raw compute performance?

A: The 940MX delivers 881.7 GFLOPS of FP32 performance, while the P400 delivers 641.0 GFLOPS. This represents a 37.5% advantage for the 940MX in raw single-precision floating-point throughput.

Q: Which GPU wins the Vulkan benchmark?

A: The Quadro P400 wins the Geekbench Vulkan test with a score of 5119, beating the 940MX’s 4749 by 7.2%. This indicates the P400 has a stronger graphics API performance profile.

Q: What is the memory bandwidth difference between the two?

A: The 940MX has significantly higher memory bandwidth at 40.10 GB/s, compared to the P400’s 32.06 GB/s. Both use 2 GB of GDDR5 memory with a 64-bit bus, but the 940MX runs its memory at 1253 MHz (5 Gbps effective) versus the P400’s 1002 MHz (4 Gbps effective).

Q: Are both cards single-slot solutions?

A: No. The Quadro P400 is a single-slot card measuring 150 mm in length and 69 mm in height, designed for a standard PCIe 3.0 x16 slot. The 940MX is an MXM Module, which is a mobile form factor with its display outputs depending on the host device.

Q: Which GPU has the newer architecture?

A: The Quadro P400 uses the Pascal architecture on a 14 nm Samsung process, while the 940MX uses the older Maxwell architecture on a 28 nm TSMC process. The P400’s chip, GP107, contains 3,300 million transistors versus the 940MX’s GM107 with 1,870 million.

Architecture Differences

The architectural gap between these two GPUs is substantial, spanning a full generation. The GeForce 940MX is built on the Maxwell architecture, using the GM107 chip manufactured on a 28 nm process at TSMC. In contrast, the Quadro P400 adopts the Pascal architecture with the GP107 chip on a more advanced 14 nm process from Samsung. This node shrink allows the P400 to pack significantly more transistors into a smaller die: 3,300 million transistors on a 132 mm² die, versus 1,870 million on a 148 mm² die for the 940MX. The transistor density jumps from 12.6 million per mm² on the 940MX to 25.0 million per mm² on the P400, a nearly 2x improvement.

The shader configuration also differs fundamentally. The 940MX packs 512 shading units, 32 texture mapping units (TMUs), and only 8 render output units (ROPs). The P400 has half the shading units at 256, with 16 TMUs, but doubles the ROP count to 16. This is a classic trade-off: the 940MX is built for wider parallel compute, while the P400’s higher ROP count suggests better pixel-pushing capability. The P400 also has a higher base clock of 1228 MHz and boost clock of 1252 MHz, compared to the 940MX’s 795 MHz base and 861 MHz boost, which partially compensates for its fewer shaders.

The P400 supports a more modern feature set under the hood. It lists DirectX 12 (12_1) support, while the 940MX only reaches DirectX 12 (11_0). Both cards support OpenGL 4.6 and Vulkan 1.4, so API compatibility is otherwise equal. The P400 also has a formal FP16 rating of 10.02 GFLOPS (at a 1:64 ratio), whereas the 940MX has no listed FP16 capability, indicating the Maxwell part lacks dedicated half-precision support.

Head-to-Head Benchmarks

The two benchmark results paint a picture of complementary strengths. In the Geekbench OpenCL test, the GeForce 940MX scores 4939 against the Quadro P400’s 4249, a 16.2% advantage for the Maxwell card. This aligns with its higher FP32 throughput (881.7 GFLOPS vs 641.0 GFLOPS) and wider shader count. The OpenCL result is a compute-oriented workload, and the 940MX’s 512 shading units clearly outpace the P400’s 256 units in this scenario.

The tables turn in the Geekbench Vulkan test. Here, the Quadro P400 scores 5119, defeating the 940MX’s 4749 by 7.2%. Vulkan is a lower-level graphics API that often benefits from architecture efficiency and driver optimization. Despite having half the shader cores, the P400’s higher clocks (1228 MHz base) and doubled ROP count (16 vs 8) help it pull ahead in this graphics-focused benchmark. The P400’s pixel rate of 20.03 GPixel/s is nearly triple the 940MX’s 6.888 GPixel/s, which explains its Vulkan advantage.

The texture rate comparison is also telling. The 940MX delivers 27.55 GTexel/s, while the P400 manages 20.03 GTexel/s. This is a 37.5% lead for the 940MX in texture fill, consistent with its 32 TMUs versus the P400’s 16. The net result is that the 940MX wins one benchmark and the P400 wins the other, each by a meaningful margin.

Specification Differences

The specification sheets reveal distinct design philosophies. The most obvious difference is form factor: the 940MX is an MXM Module with portable-device-dependent display outputs, while the P400 is a single-slot, 150 mm long (5.9 inches) and 69 mm tall (2.7 inches) card with 3x mini-DisplayPort 1.4a outputs. The P400 is a standard PCIe 3.0 x16 card, while the 940MX uses a narrower PCIe 3.0 x8 interface.

Memory clocks differ despite identical memory size and type. The 940MX runs its GDDR5 at 1253 MHz (5 Gbps effective), yielding a bandwidth of 40.10 GB/s. The P400’s GDDR5 runs at 1002 MHz (4 Gbps effective), producing 32.06 GB/s bandwidth. This is a 25% bandwidth advantage for the 940MX.

Power consumption is also different. The 940MX has a TDP of 23 W, while the P400 has a TDP of 30 W. Neither card requires external power connectors, but the P400 lists a suggested PSU of 200 W, while the 940MX has no such recommendation. The P400’s higher ROP count and clock speeds require more power, but both remain low-power solutions.

The transistor counts reflect the process node advantage. The P400’s GP107 chip has 3,300 million transistors on a 132 mm² die, while the 940MX’s GM107 has 1,870 million on a larger 148 mm² die. The P400’s 14 nm process enables a 76% increase in transistor count within a 10.8% smaller die area.

Where Each One Wins

The GeForce 940MX is the compute-oriented card. Its 16.2% OpenCL lead, 37.5% higher FP32 throughput, and 25% memory bandwidth advantage make it the better choice for raw general-purpose compute tasks. With 512 shading units and 32 TMUs, it excels in workloads that scale with shader count, such as physics simulations or OpenCL-based rendering. Its lower TDP of 23 W also makes it more suitable for power-constrained mobile chassis, given its MXM form factor.

The Quadro P400 is the graphics-centric card. Its 7.2% Vulkan win, 20.03 GPixel/s pixel rate, and 16 ROPs give it a clear edge in rasterization-heavy tasks. The P400’s DirectX 12 (12_1) support is a generation ahead of the 940MX’s (11_0), which matters for modern game engines or professional D3D12 applications. Its 3x mini-DisplayPort 1.4a outputs also make it a practical multi-monitor workstation solution, unlike the 940MX’s device-dependent outputs.

The P400’s higher base clock (1228 MHz vs 795 MHz) means it processes instructions faster per core, benefiting latency-sensitive workloads. Its 10.02 GFLOPS FP16 rating, while low, indicates some half-precision capability that the 940MX lacks entirely.

The Verdict

The data supports a clear split based on workload type. For users prioritizing OpenCL compute performance and memory bandwidth, the GeForce 940MX is the superior choice — its 16.2% OpenCL lead and 40.10 GB/s bandwidth are decisive. It is also the better option for thermal-sensitive mobile deployments, given its 23 W TDP and MXM form factor.

For users needing Vulkan performance and professional display connectivity, the Quadro P400 is the answer. Its 7.2% Vulkan advantage, 20.03 GPixel/s pixel rate, and triple mini-DisplayPort outputs make it a more capable graphics workstation card. The P400’s DirectX 12 (12_1) support and PCIe 3.0 x16 interface also future-proof it better for modern APIs and system integration.

In the broader context, both cards sit near the bottom of the performance spectrum — the 940MX at the 28th percentile and the P400 at the 27th. The 940MX’s nearest rivals include the GeForce GTX 560M (4855, 0.2% behind) and GTS 450 (4893, 1% behind), while the P400’s rivals include the Radeon R8 M445DX (4727, 0.9% ahead) and GTX 970M (4628, 1.2% behind). Neither card is a performance king, but each serves its niche: the 940MX for compute-light mobile tasks, and the P400 for compact professional graphics. Choose the 940MX for OpenCL-heavy, bandwidth-sensitive workloads; choose the P400 for Vulkan-based graphics and multi-display setups.