NVIDIA GeForce GTX 870M vs NVIDIA Quadro M2000M Comparison

Head-to-Head Benchmarks

The only directly comparable benchmark between these two mobile GPUs is Geekbench OpenCL, and the data shows a decisive win for the NVIDIA GeForce GTX 870M. It scores 12,630 against the Quadro M2000M's 10,057, a 25.6% advantage in raw compute throughput. That is not a marginal gap; it is the kind of margin that translates into visibly faster performance in any OpenCL-accelerated workload.

Looking at the broader benchmark picture, the GTX 870M's average benchmark score across all tests it appears in is 9,959, while the Quadro M2000M sits at 9,832. The difference is only 1.3%, which might suggest they are close overall. But that average is skewed by the fact that the GTX 870M has a Geekbench Metal score of 7,288 — a test the Quadro M2000M does not appear in — while the Quadro has a Geekbench Vulkan score of 9,606 that the GTX 870M lacks. In the one test where they go head-to-head, the GTX 870M wins by a wide margin.

The percentile rankings tell a similar story. The GTX 870M sits at the 48th percentile of all GPUs, while the Quadro M2000M is at the 47th. That is nearly identical positioning in the overall performance hierarchy, but the OpenCL delta shows the GTX 870M punches harder in that specific API.

Rival comparisons reinforce the picture. The GTX 870M's nearest rival is the AMD Radeon Pro 5300M, which averages 10,013 — just 0.5% higher. The NVIDIA Quadro K5100M is 0.8% ahead at 10,043. The GTX 870M also edges out the NVIDIA Quadro 6000 by 1.1%. For the Quadro M2000M, its closest rival is the NVIDIA Quadro 6000 at 9,846, which is just 0.1% ahead. The AMD FirePro W5000 trails by 0.3%, and the NVIDIA GeForce GTX 1070 is 0.5% behind the Quadro M2000M. The GTX 870M's 25.6% OpenCL win over the Quadro M2000M is far larger than any of these inter-brand rival deltas.

Where Each One Wins

The GTX 870M wins the only shared benchmark, and it wins by a lot. If your workload is OpenCL-compute heavy — think rendering, physics simulation, or any GPGPU task that leverages that API — the data points squarely at the GTX 870M. Its shading unit count of 1,344 versus the Quadro M2000M's 640 is the obvious structural reason, and the 25.6% OpenCL delta confirms it in practice.

The Quadro M2000M does not win any head-to-head benchmark in this data set, but it does have a Vulkan score of 9,606, which the GTX 870M cannot match because it has no Vulkan result listed. If your application uses Vulkan, the Quadro M2000M offers a measurable performance data point that the GTX 870M simply does not provide. That is not a win in the head-to-head sense, but it is a functional advantage for Vulkan-specific workloads.

The Quadro M2000M also has double the memory capacity at 4 GB versus 3 GB. For workloads that exceed 3 GB of VRAM — large textures, complex CAD models, or multi-layer compositing — the Quadro M2000M will not run out of memory where the GTX 870M would. That is a capacity advantage, not a speed advantage, but it can be the deciding factor in professional applications.

The GTX 870M carries a 100 W TDP, while the Quadro M2000M draws only 55 W. In a laptop chassis, that 45 W difference is substantial. The Quadro M2000M will generate less heat and place less demand on the cooling solution and battery. For mobile workstations where sustained performance under load matters, the lower power draw can translate into more consistent clocks and a quieter system.

Architecture Differences

The two GPUs come from different NVIDIA architectures. The GTX 870M is built on Kepler, using the GK104 chip, while the Quadro M2000M uses Maxwell with the GM107 chip. Both are manufactured on the same 28 nm process at TSMC, but the transistor budgets differ enormously. The GK104 packs 3,540 million transistors into a 294 mm² die, giving a transistor density of 12.0 million per mm². The GM107 contains 1,870 million transistors on a 148 mm² die, with a slightly higher density of 12.6 million per mm². The GTX 870M's die is nearly twice the physical size and holds nearly twice the transistors.

The compute resources reflect that difference. The GTX 870M has 1,344 shading units, 112 texture mapping units, and 24 ROPs. The Quadro M2000M has 640 shading units, 40 TMUs, and 16 ROPs. That is roughly half the shading units and less than half the texture units. Pixel rate is 27.08 GPixel/s for the GTX 870M versus 18.19 GPixel/s for the Quadro M2000M. Texture rate is 108.3 GTexel/s against 45.48 GTexel/s. FP32 compute is 2.599 TFLOPS for the GTX 870M and 1,455.4 GFLOPS for the Quadro M2000M.

Memory systems diverge as well. The GTX 870M uses a 192-bit bus with 3 GB of GDDR5 and 120.0 GB/s of bandwidth. The Quadro M2000M has a narrower 128-bit bus with 4 GB of GDDR5 and 80.19 GB/s of bandwidth. Even though the Quadro has more capacity, it has 33% less bandwidth. Clock speeds are higher on the Quadro — 1,098 MHz base and 1,137 MHz boost versus 941 MHz and 967 MHz — but the GTX 870M's wider architecture overcomes that clock disadvantage. Memory clocks are essentially identical at 1,250 MHz versus 1,253 MHz, both delivering 5 Gbps effective.

The bus interface differs too: the GTX 870M uses MXM-B (3.0), while the Quadro M2000M uses MXM-A (3.0). Both are MXM modules with no power connectors and portable-device-dependent display outputs. API support is similar — both support DirectX 12 (11_0), OpenGL 4.6, and Vulkan, though the Quadro lists Vulkan 1.4 while the GTX 870M lists Vulkan 1.2.175.

FAQ

Q: Which GPU has higher raw compute performance in OpenCL?

A: The NVIDIA GeForce GTX 870M. It scores 12,630 in Geekbench OpenCL versus 10,057 for the Quadro M2000M, a 25.6% advantage.

Q: Does the Quadro M2000M have any benchmark where it beats the GTX 870M?

A: No. In the only shared benchmark (Geekbench OpenCL), the GTX 870M wins. The Quadro M2000M does have a Geekbench Vulkan score of 9,606, but no Vulkan result is listed for the GTX 870M, so no direct comparison is possible.

Q: How much memory does each GPU have?

A: The GTX 870M has 3 GB of GDDR5 on a 192-bit bus with 120.0 GB/s bandwidth. The Quadro M2000M has 4 GB of GDDR5 on a 128-bit bus with 80.19 GB/s bandwidth.

Q: Which GPU is more power-efficient?

A: The Quadro M2000M has a 55 W TDP, while the GTX 870M has a 100 W TDP. The Quadro draws 45 W less, making it significantly easier on laptop cooling and battery life.

Q: What are the architecture differences between the two?

A: The GTX 870M uses Kepler (GK104) with 3,540 million transistors on a 294 mm² die. The Quadro M2000M uses Maxwell (GM107) with 1,870 million transistors on a 148 mm² die. Both are 28 nm TSMC parts.

Q: How do these GPUs rank relative to all other GPUs?

A: The GTX 870M is at the 48th percentile, and the Quadro M2000M is at the 47th percentile. Their average benchmark scores are 9,959 and 9,832, respectively.

Specification Differences

| Specification | NVIDIA GeForce GTX 870M | NVIDIA Quadro M2000M |

|---|---|---|

| Chip | GK104 | GM107 |

| Architecture | Kepler | Maxwell |

| Generation | GeForce 800M | Quadro Maxwell-M (Mx000M) |

| Process Node | 28 nm | 28 nm |

| Transistors | 3,540 million | 1,870 million |

| Die Size | 294 mm² | 148 mm² |

| Transistor Density | 12.0M / mm² | 12.6M / mm² |

| Base Clock | 941 MHz | 1,098 MHz |

| Boost Clock | 967 MHz | 1,137 MHz |

| Memory Clock | 1,250 MHz (5 Gbps effective) | 1,253 MHz (5 Gbps effective) |

| Memory Size | 3 GB | 4 GB |

| Memory Bus Width | 192 bit | 128 bit |

| Memory Bandwidth | 120.0 GB/s | 80.19 GB/s |

| Shading Units | 1,344 | 640 |

| TMUs | 112 | 40 |

| ROPs | 24 | 16 |

| Pixel Rate | 27.08 GPixel/s | 18.19 GPixel/s |

| Texture Rate | 108.3 GTexel/s | 45.48 GTexel/s |

| FP32 Compute | 2.599 TFLOPS | 1,455.4 GFLOPS |

| TDP | 100 W | 55 W |

| Bus Interface | MXM-B (3.0) | MXM-A (3.0) |

| Vulkan Version | 1.2.175 | 1.4 |

| Release Date | 2014-03-11 | 2015-12-02 |

| Predecessor | GeForce 700M | Quadro Kepler-M |

| Successor | GeForce 900M | Quadro Pascal-M |

The Verdict

The data is unambiguous in the shared benchmark: the GTX 870M is 25.6% faster in OpenCL, and it has nearly double the shading units, texture units, and FP32 compute. For any workload that uses OpenCL, the GTX 870M is the stronger performer. Its 120.0 GB/s of memory bandwidth versus 80.19 GB/s also gives it a clear edge in memory-throughput-bound tasks.

The Quadro M2000M's case rests on different pillars. It has 4 GB of VRAM versus 3 GB, which matters for larger datasets. It draws 55 W versus 100 W, making it the better choice for thermally constrained laptops. It has a Vulkan score of 9,606, offering a data point for Vulkan applications that the GTX 870M cannot match. And it is built on Maxwell, which is a newer architecture generation than Kepler, even though both are 28 nm parts.

The GTX 870M was released earlier (2014-03-11) than the Quadro M2000M (2015-12-02), but release date does not translate into performance here. The GTX 870M's average benchmark score is 9,959 against 9,832, a 1.3% overall edge. The percentile rankings are essentially tied at 48 versus 47.

For a builder choosing between these two for a mobile workstation, the decision hinges on workload. If OpenCL performance is the priority — and the benchmark data says it is the only directly comparable metric — the GTX 870M is the clear pick. If memory capacity, power draw, or Vulkan support are the primary requirements, the Quadro M2000M has the advantage. Both are end-of-life products, so availability and driver support are historical considerations rather than forward-looking ones.

The practical advice: pick the GTX 870M for compute-heavy tasks that use OpenCL, pick the Quadro M2000M for larger VRAM footprints, lower power envelopes, or Vulkan-based applications. The GTX 870M wins the performance crown in the one test that matters most for comparison, but the Quadro M2000M offers capabilities the GTX 870M simply does not have.