NVIDIA GeForce 920MX vs NVIDIA Quadro K2000 Comparison

FAQ

Q: Which GPU has the higher average benchmark score in the database?

A: The NVIDIA Quadro K2000 averages 3964 points, while the NVIDIA GeForce 920MX averages 3528 points, a difference of 436 points in favor of the Quadro.

Q: How do the two cards compare in the OpenCL benchmark?

A: They are nearly identical. The Quadro K2000 scores 4071, the GeForce 920MX scores 4068, and the Quadro leads by only 0.1%.

Q: What does the Vulkan benchmark show about the Quadro K2000's advantage?

A: The Quadro K2000 scores 4191 in Vulkan, versus 2987 for the GeForce 920MX, a lead of 40.3%.

Q: What is the memory configuration difference between the two cards?

A: Both have 2 GB of memory, but the Quadro K2000 uses GDDR5 on a 128-bit bus with 64.00 GB/s bandwidth, while the GeForce 920MX uses DDR3 on a 64-bit bus with 14.40 GB/s bandwidth.

Q: Which card has the higher transistor density despite having fewer transistors?

A: The GeForce 920MX, based on the GM108S chip, has 1,020 million transistors on a 77 mm² die, yielding 13.2M transistors per mm². The Quadro K2000 has 1,270 million transistors on a 118 mm² die, for 10.8M per mm².

Q: What is the TDP difference between the two?

A: The Quadro K2000 is rated at 51 W, while the GeForce 920MX is rated at 16 W, making the 920MX considerably more power-efficient.

Where Each One Wins

The data splits along compute workloads. The Quadro K2000 wins both recorded head-to-head benchmarks, taking 2 wins out of two tests. The GeForce 920MX does not win a single test in the database. However, the two cards serve very different usage contexts that affect which strengths matter.

For OpenCL workloads, the gap is essentially a tie at 0.1%, so neither card can claim a meaningful win there. The Quadro's only substantial edge appears in Vulkan, where it beats the 920MX by 40.3%. Users running Vulkan workloads on the Quadro should expect a clear performance class difference. The 920MX's Vulkan score of 2987 sits near its rivals: the GeForce GT 545 averages 3594 (1.8% above the 920MX), the RTX 5000 Mobile Ada Generation averages 3596 (1.9% above), and the GeForce GT 735M averages 3616 (2.4% above). The Quadro 2000M averages 3434, 2.7% below the 920MX. So the 920MX lands in a cluster of older and mobile parts, all within a few percent of each other.

The Quadro K2000's average score places it at the 24th percentile of all GPUs in the database, compared to the 920MX at the 21st percentile. Its nearest rivals include the GeForce 830M (0.2% behind the Quadro), the Radeon R5 M420 (0.2% behind), and the GeForce GT 745M (0.3% behind), with the Radeon HD 6850 X2 0.3% ahead. This places the Quadro in a tight pack of mid-range mobile and older desktop parts, while the 920MX sits in a slightly lower performance tier.

For the 920MX, the practical win is in power draw and portability. Its 16 W TDP, MXM module form factor, and PCIe 3.0 x8 interface suit thin laptops. The Quadro K2000, with a 51 W TDP, single-slot design, and PCIe 2.0 x16 interface, is built for workstations with more room for expansion. The 920MX also supports Vulkan 1.4, a newer API version than the Quadro K2000's Vulkan 1.2.175, which matters for software compatibility.

Architecture Differences

The two chips come from different NVIDIA architectures and generations. The Quadro K2000 uses the GK107 chip on the Kepler architecture, from the Quadro Kepler (Kx000) generation. The GeForce 920MX uses the GM108S chip on the Maxwell architecture, from the GeForce 900M generation. Both are built by TSMC on a 28 nm process.

The Quadro K2000 carries 1,270 million transistors on a 118 mm² die, giving a transistor density of 10.8M per mm². The GeForce 920MX has 1,020 million transistors on a 77 mm² die, for 13.2M per mm². Despite having fewer transistors, the 920MX packs them more densely.

Compute resources differ notably. The Quadro K2000 has 384 shading units, 32 texture mapping units, and 16 ROPs. The GeForce 920MX has 256 shading units, 24 TMUs, and 8 ROPs. The Quadro carries 50% more shading units and double the ROP count. Neither card includes ray tracing cores or tensor cores.

The memory architecture differs sharply. The Quadro K2000 uses 2 GB of GDDR5 on a 128-bit bus with 64.00 GB/s bandwidth. The GeForce 920MX uses 2 GB of DDR3 on a 64-bit bus with 14.40 GB/s bandwidth, less than a quarter of the Quadro's bandwidth.

Interface and form factor also differ. The Quadro K2000 uses PCIe 2.0 x16 and is a single-slot, full-length card at 202 mm (8 inches) long and 111 mm (4.4 inches) tall. The GeForce 920MX uses PCIe 3.0 x8 and is an MXM module with no listed dimensions, designed for portable devices.

API support differs slightly. Both support DirectX 12 (11_0) and OpenGL 4.6. The Quadro supports Vulkan 1.2.175, while the GeForce 920MX supports Vulkan 1.4.

Specification Differences

The two GPUs differ in clock behavior. The Quadro K2000 lists no base or boost clock, only a memory clock of 1000 MHz with 4 Gbps effective. The GeForce 920MX lists a base clock of 965 MHz, a boost clock of 993 MHz, and a memory clock of 900 MHz with 1800 Mbps effective.

The Quadro K2000 produces a pixel rate of 7.632 GPixel/s and a texture rate of 30.53 GTexel/s, with FP32 compute of 732.7 GFLOPS. The GeForce 920MX produces a pixel rate of 7.944 GPixel/s and a texture rate of 23.83 GTexel/s, with FP32 compute of 508.4 GFLOPS. The Quadro has higher texture rate and higher FP32, while the 920MX has a slightly higher pixel rate.

The Quadro K2000 has a TDP of 51 W, a suggested PSU of 250 W, no power connectors, a single-slot width, and display outputs of 1x DVI and 2x DisplayPort 1.2. The GeForce 920MX has a TDP of 16 W, no suggested PSU, no power connectors, an MXM module slot width, and display outputs that are portable-device dependent.

The Quadro K2000 was released on 2013-02-28, with a launch MSRP of 599 USD. The GeForce 920MX was released on 2016-03-24, with no launch MSRP recorded. Both are end-of-life products. The Quadro's predecessor is Quadro Fermi and its successor is Quadro Maxwell. The 920MX's predecessor is GeForce 800M and its successor is GeForce 10 Mobile.

Head-to-Head Benchmarks

Two benchmark comparisons are recorded between these cards. In Geekbench OpenCL, the Quadro K2000 scores 4071 and the GeForce 920MX scores 4068. The Quadro wins by 0.1%, a margin that is effectively negligible. Both cards deliver essentially identical OpenCL performance despite their different architectures and memory systems.

In Geekbench Vulkan, the gap is much larger. The Quadro K2000 scores 4191, while the GeForce 920MX scores 2987. The Quadro wins by 40.3%. This is the dominant result between the two cards. The Quadro's Vulkan score is also higher than its own OpenCL score, while the 920MX's Vulkan score is far lower than its OpenCL score.

Looking at the average benchmark scores, the Quadro K2000's 3964 average is 12.4% above the 920MX's 3528 average. The Quadro's 24th percentile placement versus the 920MX's 21st percentile confirms the hierarchy.

The Quadro K2000's nearest rival, the GeForce 830M, averages 3957, only 0.2% below the Quadro. The Radeon R5 M420 averages 3956, also 0.2% below. The GeForce GT 745M averages 3953, 0.3% below. The AMD Radeon HD 6850 X2 averages 3977, 0.3% above. The Quadro sits right in the middle of this cluster.

The GeForce 920MX's nearest rivals cluster lower. The GeForce GT 545 averages 3594, 1.8% above the 920MX. The RTX 5000 Mobile Ada Generation averages 3596, 1.9% above. The GeForce GT 735M averages 3616, 2.4% above. The Quadro 2000M averages 3434, 2.7% below. The 920MX's average sits below all but one of its nearest rivals.

The Verdict

The data points to the NVIDIA Quadro K2000 as the stronger GPU in compute performance. It wins both head-to-head benchmarks, holds a 12.4% higher average score, and ranks at a higher percentile. Users who run Vulkan workloads should choose the Quadro K2000, as it leads the 920MX by 40.3% in that test. Users who run OpenCL workloads will see virtually no difference, with the Quadro ahead by only 0.1%.

The GeForce 920MX is the better choice for power-constrained portable systems. Its 16 W TDP is less than a third of the Quadro K2000's 51 W TDP. It comes as an MXM module, has no power connectors, and its display outputs are portable-device dependent, which signals a laptop-oriented design. Its base clock of 965 MHz and boost clock of 993 MHz are explicitly listed, while the Quadro K2000 lists no base or boost clock at all.

The memory comparison strongly favors the Quadro K2000. Its GDDR5 memory on a 128-bit bus delivers 64.00 GB/s, versus the 920MX's DDR3 on a 64-bit bus at 14.40 GB/s. This bandwidth advantage, combined with more shading units and double the ROPs, explains the Quadro's higher FP32 compute of 732.7 GFLOPS versus 508.4 GFLOPS.

The Quadro K2000 also offers workstation-oriented features: a single-slot design, PCIe 2.0 x16 interface, and dedicated display outputs of 1x DVI and 2x DisplayPort 1.2. Its 250 W suggested PSU and 599 USD launch MSRP reflect its professional positioning. The 920MX lacks a recorded launch MSRP and uses PCIe 3.0 x8, which suits a mobile platform.

For buyers selecting between these two end-of-life GPUs, the decision rests on workload and system type. Desktop workstation users with Vulkan or mixed compute tasks should take the Quadro K2000. Users building or upgrading a low-power laptop and running primarily OpenCL workloads can use the GeForce 920MX without sacrificing much compute performance, but should expect markedly weaker Vulkan results and lower overall average scores.