NVIDIA GeForce GTX 870M vs NVIDIA RTX PRO 6000D Blackwell Max-Q Comparison

NVIDIA
GEFORCE

NVIDIA GeForce GTX 870M

CORE STATE GK104
VRAM 3 GB
CLOCK SPEED 967 MHz
TDP 100 W
BUS WIDTH 192 bit
ARCHITECTURE Kepler
nm
PROCESS 28 nm
LAUNCH DATE 2014
VS
NVIDIA
GEFORCE

RTX PRO 6000D Blackwell Max-Q

CORE STATE GB202
VRAM 96 GB
CLOCK SPEED 2288 MHz
TDP 300 W
BUS WIDTH 512 bit
ARCHITECTURE Blackwell 2.0
nm
PROCESS 5 nm
LAUNCH DATE 2025

PERFORMANCE BENCHMARKS

geekbench_metal
7,288
N/A
geekbench_opencl
12,630
N/A
3dmark_3dmark_steel_nomad_dx12
N/A
11,088

Analysis: NVIDIA GeForce GTX 870M vs NVIDIA RTX PRO 6000D Blackwell Max-Q

The NVIDIA RTX PRO 6000D Blackwell Max-Q and the NVIDIA GeForce GTX 870M represent two distant generations of GPU design, separated by over a decade of architectural evolution. The former is a 2025 workstation flagship built on Blackwell 2.0, while the latter is a 2014 mobile part based on Kepler. Benchmark results place them close in aggregate scoring despite wildly different specifications, but a closer look reveals how each achieves its position.

Head-to-Head Benchmarks

The direct comparison is complicated by the fact that the two cards were tested under different benchmark suites. The RTX PRO 6000D Blackwell Max-Q has a single recorded score in 3DMark Steel Nomad DX12: 11,088 points. The GTX 870M has scores in Geekbench Metal (7,288) and Geekbench OpenCL (12,630), producing an average benchmark score of 9,959 across its tests. When comparing average scores, the RTX PRO 6000D leads by 1,129 points, or approximately 11.3% over the GTX 870M.

However, the percentile rankings tell a different story. The RTX PRO 6000D sits at the 50th percentile among all GPUs, while the GTX 870M sits at the 48th percentile. This narrow 2-percentile gap suggests that in the broader landscape of all tested GPUs, these two cards occupy nearly the same tier of overall performance. The RTX PRO 6000D’s nearest rivals include the AMD Radeon RX 550 (avg score 11,075, delta 0.1%) and the NVIDIA GeForce GTX 1650 SUPER (avg score 11,047, delta 0.4%), meaning the RTX PRO 6000D is essentially tied with those cards. The AMD FirePro W4300 scores 11,225, which is 1.2% higher than the RTX PRO 6000D.

For the GTX 870M, its nearest rivals are all within a tight band. The AMD Radeon Pro 5300M scores 10,013 (0.5% higher), the NVIDIA Quadro K5100M scores 10,043 (0.8% higher), and the AMD Radeon R9 M375 scores 10,070 (1.1% higher). The NVIDIA Quadro 6000 scores 9,846, which is 1.1% lower than the GTX 870M. This clustering indicates that the GTX 870M performs competitively with a range of mid-range and older workstation cards, despite its age.

The head-to-head benchmark list is empty, so no direct same-test comparison exists. The only cross-suite inference is through average scores: the RTX PRO 6000D’s 11,088 versus the GTX 870M’s 9,959. That 1,129-point gap is significant in raw terms, but the percentile proximity suggests that in real-world tasks, the perceived difference may be smaller than the spec sheets imply.

Where Each One Wins

The RTX PRO 6000D Blackwell Max-Q wins decisively in raw computational throughput. Its FP32 performance is 110.1 TFLOPS, a figure that dwarfs the GTX 870M’s 2.599 TFLOPS — a 42-fold difference. This makes the RTX PRO 6000D suited for compute-heavy workloads such as simulation, rendering, and AI inference, where massive parallel throughput is essential. Its texture rate of 1,720.6 GTexel/s versus 108.3 GTexel/s on the GTX 870M further cements its dominance in geometry-heavy scenes.

The GTX 870M wins in energy efficiency per task, though the data is indirect. Its TDP is 100 W, compared to 300 W on the RTX PRO 6000D. That means the GTX 870M delivers its 9,959 average benchmark score at one-third the power draw. For portable devices, this efficiency is the primary advantage. The GTX 870M also has a production status of End-of-life, meaning it is a legacy part; the RTX PRO 6000D is Active. In legacy compatibility, the GTX 870M supports Vulkan 1.2.175, while the RTX PRO 6000D supports Vulkan 1.4 — the newer card has broader API support.

Where the GTX 870M wins is in the Geekbench OpenCL test specifically, scoring 12,630, which is higher than the RTX PRO 6000D’s single 3DMark score. However, these are different tests, so a direct comparison is invalid. The GTX 870M’s average score of 9,959 is within 10% of the RTX PRO 6000D’s average of 11,088, suggesting that in certain lightweight or legacy workloads, the older card remains viable.

Architecture Differences

The architectural gap is vast. The RTX PRO 6000D uses the GB202 chip on a 5 nm process from TSMC, with 92,200 million transistors on a 750 mm² die. The transistor density is 122.9 million per square millimeter. The GTX 870M uses the GK104 chip on a 28 nm process, also from TSMC, with 3,540 million transistors on a 294 mm² die. Its transistor density is 12.0 million per square millimeter — roughly ten times lower.

Memory configurations differ enormously. The RTX PRO 6000D has 96 GB of GDDR7 on a 512-bit bus, delivering 1.79 TB/s bandwidth. The GTX 870M has 3 GB of GDDR5 on a 192-bit bus, delivering 120.0 GB/s. That is a 15-fold difference in memory capacity and a 14.9-fold difference in bandwidth.

The compute resources are similarly divergent. The RTX PRO 6000D has 24,064 shading units, 752 TMUs, 192 ROPs, 188 RT cores, and 752 tensor cores. The GTX 870M has 1,344 shading units, 112 TMUs, 24 ROPs, and no RT or tensor cores. The RTX PRO 6000D supports DirectX 12 Ultimate (12_2), while the GTX 870M supports DirectX 12 (11_0). Both support OpenGL 4.6.

Clock speeds are lower on the RTX PRO 6000D in raw terms — base 1590 MHz and boost 2288 MHz versus 941 MHz base and 967 MHz boost on the GTX 870M — but the massive increase in execution units makes the newer card far faster overall. The RTX PRO 6000D’s pixel rate is 439.3 GPixel/s versus 27.08 GPixel/s on the GTX 870M.

The RTX PRO 6000D uses PCIe 5.0 x16, while the GTX 870M uses MXM-B (3.0). The newer card has four DisplayPort 2.1b outputs; the GTX 870M’s outputs are portable-device dependent. The RTX PRO 6000D is dual-slot with a 16-pin power connector and a suggested PSU of 700 W. The GTX 870M is an MXM module with no dedicated power connectors.

FAQ

Q: Which card has higher raw FP32 performance?

A: The RTX PRO 6000D Blackwell Max-Q has 110.1 TFLOPS FP32, versus 2.599 TFLOPS on the GTX 870M. That is a 42-fold difference.

Q: How do their memory bandwidths compare?

A: The RTX PRO 6000D has 1.79 TB/s bandwidth from 96 GB of GDDR7 on a 512-bit bus. The GTX 870M has 120.0 GB/s from 3 GB of GDDR5 on a 192-bit bus.

Q: Are they in the same performance percentile?

A: Yes. The RTX PRO 6000D is at the 50th percentile among all GPUs, and the GTX 870M is at the 48th percentile. Their average benchmark scores are 11,088 and 9,959, respectively.

Q: Does the GTX 870M support ray tracing?

A: No. The GTX 870M has no RT cores or tensor cores. The RTX PRO 6000D has 188 RT cores and 752 tensor cores.

Q: What is the power consumption difference?

A: The RTX PRO 6000D has a TDP of 300 W, while the GTX 870M has a TDP of 100 W. The newer card draws three times as much power.

Q: Which card is still in production?

A: The RTX PRO 6000D is Active, while the GTX 870M is End-of-life. The GTX 870M was released in 2014; the RTX PRO 6000D was released in 2025.

The Verdict

The data points to a clear split by use case. The RTX PRO 6000D Blackwell Max-Q is the choice for any workload that demands extreme compute throughput, massive memory capacity, or modern API features. Its 110.1 TFLOPS FP32, 96 GB of memory, and support for DirectX 12 Ultimate make it suitable for professional visualization, AI training, and large-scale rendering. Its 300 W TDP and dual-slot design require a robust power supply and chassis, but the performance justifies the infrastructure.

The GTX 870M is a legacy mobile part that still holds its own in aggregate benchmark scores, sitting just 2 percentile points below the RTX PRO 6000D. Its 100 W TDP and MXM form factor make it appropriate for older portable workstations or embedded systems where power efficiency and space are critical. It lacks ray tracing and tensor cores, so it is unsuitable for modern AI or ray-traced workloads, but for basic 3D acceleration and OpenCL compute, it remains competitive with cards like the AMD Radeon Pro 5300M and NVIDIA Quadro K5100M.

If the requirement is maximum performance per watt in a compact module, the GTX 870M has a place. If the requirement is absolute performance and future-proofing, the RTX PRO 6000D is the only viable option. The benchmark scores are close in percentile terms, but the architectural gulf means they serve entirely different markets. The RTX PRO 6000D is a workstation-class tool; the GTX 870M is a legacy efficiency part. Choose based on workload, not raw scores.

DETAILED SPECIFICATIONS

SPECIFICATION
GTX 870M
RTX PRO 6000D Blackwell Max-Q
Core Specs
Shading Units
1,344
24,064 +1690.5%
Shaders
1,344
24,064 +1690.5%
TMUs
112
752 +571.4%
ROPs
24
192 +700.0%
SM Count
—
188
Clocks
Base Clock
941 MHz
1590 MHz
Boost Clock
967 MHz
2288 MHz
Memory Clock
1250 MHz 5 Gbps effective
1750 MHz 28 Gbps effective
Memory
Memory Size
3 GB
96 GB
VRAM (MB)
3,072
98,304 +3100.0%
Memory Type
GDDR5
GDDR7
Memory Bus
192 bit
512 bit
Bandwidth
120.0 GB/s
1.79 TB/s
Cache
L1 Cache
16 KB (per SMX)
128 KB (per SM)
L2 Cache
384 KB
128 MB
Performance
Pixel Rate
27.08 GPixel/s
439.3 GPixel/s
Texture Rate
108.3 GTexel/s
1,720.6 GTexel/s
FP32 (TFLOPS)
2.599 TFLOPS
110.1 TFLOPS
FP64 (TFLOPS)
108.3 GFLOPS (1:24)
1.721 TFLOPS (1:64)
FP16 (TFLOPS)
—
110.1 TFLOPS (1:1)
AI/RT
RT Cores
—
188
Tensor Cores
—
752
Power
TDP
100 W
300 W
TDP (W)
100
300 +200.0%
Suggested PSU
—
700 W
Power Connectors
None
1x 16-pin
Architecture
Architecture
Kepler
Blackwell 2.0
GPU Name
GK104
GB202
Generation
GeForce 800M
Blackwell PRO W (x000)
Process Size
28 nm
5 nm
Transistors
3,540 million
92,200 million
Die Size
294 mm²
750 mm²
Foundry
TSMC
TSMC
Density
12.0M / mm²
122.9M / mm²
API Support
DirectX
12 (11_0)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.2.175
1.4
OpenCL
3.0
3.0
CUDA
3.0
12.0
Shader Model
6.5 (5.1)
6.9
Physical
Slot Width
MXM Module
Dual-slot
Length
—
267 mm 10.5 inches
Height
—
111 mm 4.4 inches
Outputs
Portable Device Dependent
4x DisplayPort 2.1b
Bus Interface
MXM-B (3.0)
PCIe 5.0 x16
Other
Launch Price
—
8,565 USD
Production
End-of-life
Active
Predecessor
GeForce 700M
Workstation Ada
Successor
GeForce 900M
—
View GeForce GTX 870M Details View RTX PRO 6000D Blackwell Max-Q Details