NVIDIA GeForce GTX 965M vs NVIDIA RTX PRO 6000 Blackwell Comparison

FAQ

Q: What is the performance gap between the NVIDIA RTX PRO 6000 Blackwell and the GeForce GTX 965M?

A: The two cards do not share a common benchmark in the database, so a direct head-to-head score is not recorded. However, their overall percentile positions differ: the RTX PRO 6000 Blackwell sits at the 59th percentile among all GPUs, while the GTX 965M sits at the 56th percentile. The RTX PRO 6000 Blackwell's single recorded benchmark (3DMark Steel Nomad DX12) yields a score of 16408, whereas the GTX 965M's two recorded benchmarks (Geekbench OpenCL and Vulkan) average to 14404.

Q: Which card has more memory and bandwidth?

A: The RTX PRO 6000 Blackwell ships with 96 GB of GDDR7 memory on a 512-bit bus, delivering 1.79 TB/s of bandwidth. The GTX 965M has 2 GB of GDDR5 memory on a 128-bit bus, yielding 80.19 GB/s. The RTX PRO 6000 Blackwell offers 48 times the memory capacity and over 22 times the bandwidth.

Q: Do both cards support ray tracing and tensor operations?

A: No. The RTX PRO 6000 Blackwell includes 188 RT cores and 752 tensor cores, while the GTX 965M has no recorded RT cores or tensor cores. The GTX 965M relies on Maxwell 2.0 architecture, which predates dedicated ray tracing and tensor hardware.

Q: What are the process node and transistor differences?

A: The RTX PRO 6000 Blackwell is built on TSMC's 5 nm process with 92,200 million transistors on a 750 mm² die, giving a transistor density of 122.9 million per mm². The GTX 965M uses TSMC's 28 nm process with 5,200 million transistors on a 398 mm² die, for a density of 13.1 million per mm². The newer card packs roughly 17.7 times more transistors into a die that is about 1.9 times larger.

Q: Which card is still in production?

A: The RTX PRO 6000 Blackwell has an active production status and was released on March 17, 2025. The GTX 965M is end-of-life, released on January 8, 2015, and its successor is listed as GeForce 10 Mobile.

Q: How do the nearest rivals compare for each card?

A: For the RTX PRO 6000 Blackwell, the closest rival is the AMD Radeon PRO W7500 with an average score of 16415, a delta of 0%. The NVIDIA GeForce RTX 5090 D V2 trails by 0.6% with a score of 16504. For the GTX 965M, the nearest rival is the AMD Radeon RX Vega 11 at 14385 (0.1% ahead), and the NVIDIA GeForce GTX TITAN is 0.2% ahead at 14373.

Architecture Differences

The two GPUs represent vastly different generations of NVIDIA design. The RTX PRO 6000 Blackwell uses the GB202 chip built on the Blackwell 2.0 architecture, fabricated on a 5 nm process at TSMC. The GTX 965M uses the GM204 chip based on Maxwell 2.0, also from TSMC but on a 28 nm node. This process gap alone explains much of the efficiency and density disparity: the newer chip reaches 122.9 million transistors per mm² versus 13.1 million for the older part.

The RTX PRO 6000 Blackwell is the more feature-complete design. It carries 24,064 shading units, 752 TMUs, and 192 ROPs. It also includes 188 RT cores and 752 tensor cores, which enable hardware-accelerated ray tracing and AI workloads. The GTX 965M has 1,024 shading units, 64 TMUs, and 32 ROPs, with no dedicated RT or tensor hardware. The API support reflects this: the RTX PRO 6000 Blackwell reaches DirectX 12 Ultimate (12_2), while the GTX 965M tops out at DirectX 12 (12_1). Both support OpenGL 4.6 and Vulkan 1.4.

Memory architecture is another major divider. The RTX PRO 6000 Blackwell uses GDDR7 across a 512-bit bus for 1.79 TB/s bandwidth. The GTX 965M uses GDDR5 across a 128-bit bus for 80.19 GB/s. The newer card's memory subsystem is not just faster, it is fundamentally more capable for large data sets and high-resolution workloads.

Clock speeds also tell the story of generational progress. The RTX PRO 6000 Blackwell runs at a 1590 MHz base and 2617 MHz boost, with memory at 1750 MHz (28 Gbps effective). The GTX 965M runs at 924 MHz base and 950 MHz boost, with memory at 1253 MHz (5 Gbps effective). The boost clock difference alone is over 1.6 GHz.

The form factors diverge completely. The RTX PRO 6000 Blackwell is a dual-slot PCIe 5.0 x16 card, 304 mm long, 137 mm high, and 40 mm wide, with 4x DisplayPort 2.1b outputs and a single 16-pin power connector. The GTX 965M is an MXM module using the MXM-B (3.0) interface, with no dedicated power connectors and display outputs described as "Portable Device Dependent". One is a desktop workstation card, the other is a mobile notebook component.

The Verdict

The data points to two entirely different market positions. The RTX PRO 6000 Blackwell is a current-generation workstation card with massive compute resources, 96 GB of GDDR7 memory, and hardware ray tracing and tensor cores. Its single recorded benchmark, 3DMark Steel Nomad DX12, scores 16408, placing it at the 59th percentile. It competes closely with the AMD Radeon PRO W7500 (16415, 0% delta) and sits slightly behind the NVIDIA GeForce RTX 5090 D V2 (16504, -0.6% delta). For professional workloads that need large memory capacity, high bandwidth, and modern API support, the RTX PRO 6000 Blackwell is the clear pick from this comparison.

The GTX 965M is an end-of-life mobile GPU from 2015. Its average benchmark score of 14404 comes from Geekbench OpenCL and Vulkan tests, and it sits at the 56th percentile. Its nearest rivals are integrated and older discrete parts: the AMD Radeon RX Vega 11 (14385, 0.1% ahead), the NVIDIA GeForce GTX TITAN (14373, 0.2% ahead), and the Intel Iris Xe MAX Graphics (14315, 0.6% ahead). For a legacy laptop, the GTX 965M remains serviceable, but it cannot be compared meaningfully to the RTX PRO 6000 Blackwell on any modern workload.

Who should pick which? If the requirement is a current, active workstation GPU with high memory capacity and future-proof API support, the RTX PRO 6000 Blackwell is the only option between the two. If the requirement is a historical mobile GPU for an older notebook, the GTX 965M is the relevant part, but it is end-of-life and lacks modern features like ray tracing and tensor acceleration.

Specification Differences

| Specification | RTX PRO 6000 Blackwell | GTX 965M |

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

| Chip | GB202 | GM204 |

| Architecture | Blackwell 2.0 | Maxwell 2.0 |

| Generation | Blackwell PRO W (x000) | GeForce 900M |

| Process Node | 5 nm | 28 nm |

| Transistors | 92,200 million | 5,200 million |

| Die Size | 750 mm² | 398 mm² |

| Transistor Density | 122.9M / mm² | 13.1M / mm² |

| Base Clock | 1590 MHz | 924 MHz |

| Boost Clock | 2617 MHz | 950 MHz |

| Memory Clock | 1750 MHz, 28 Gbps effective | 1253 MHz, 5 Gbps effective |

| Memory Size | 96 GB | 2 GB |

| Memory Type | GDDR7 | GDDR5 |

| Memory Bus | 512 bit | 128 bit |

| Memory Bandwidth | 1.79 TB/s | 80.19 GB/s |

| Shading Units | 24,064 | 1,024 |

| TMUs | 752 | 64 |

| ROPs | 192 | 32 |

| RT Cores | 188 | None |

| Tensor Cores | 752 | None |

| Pixel Rate | 502.5 GPixel/s | 30.40 GPixel/s |

| Texture Rate | 1,968.0 GTexel/s | 60.80 GTexel/s |

| FP32 | 126.0 TFLOPS | 1.946 TFLOPS |

| FP16 | 126.0 TFLOPS (1:1) | Not recorded |

| TDP | 600 W | Not recorded |

| Slot Width | Dual-slot | MXM Module |

| Power Connectors | 1x 16-pin | None |

| Suggested PSU | 1000 W | Not recorded |

| Bus Interface | PCIe 5.0 x16 | MXM-B (3.0) |

| Display Outputs | 4x DisplayPort 2.1b | Portable Device Dependent |

| DirectX | 12 Ultimate (12_2) | 12 (12_1) |

| OpenGL | 4.6 | 4.6 |

| Vulkan | 1.4 | 1.4 |

| Production Status | Active | End-of-life |

| Release Date | 2025-03-17 | 2015-01-08 |

| Predecessor | Workstation Ada | GeForce 800M |

| Successor | Not recorded | GeForce 10 Mobile |

| Launch MSRP | 8,565 USD | Not recorded |

Head-to-Head Benchmarks

The database does not contain shared benchmark entries between the RTX PRO 6000 Blackwell and the GTX 965M, so a direct apples-to-apples comparison on the same test is not possible. The closest available data comes from their respective nearest-rival lists and percentile standings.

The RTX PRO 6000 Blackwell's 3DMark Steel Nomad DX12 score of 16408 places it in a tight cluster with the AMD Radeon PRO W7500 at 16415 (0% delta), the AMD Radeon RX 5700 XT at 16361 (0.3% slower), and the AMD Radeon Pro 5600M at 16351 (0.4% slower). The NVIDIA GeForce RTX 5090 D V2 leads this group at 16504, meaning the RTX PRO 6000 Blackwell trails by 0.6%. This suggests the RTX PRO 6000 Blackwell is performance-competitive with mid-range to upper-mid-range GPUs in this specific DX12 workload, despite its workstation positioning.

The GTX 965M's average score of 14404 comes from Geekbench OpenCL (14509) and Geekbench Vulkan (14299). Its nearest rival, the AMD Radeon RX Vega 11, scores 14385, just 0.1% ahead. The NVIDIA GeForce GTX TITAN, a much older flagship, is 0.2% ahead at 14373. The AMD Radeon Vega 11 and Intel Iris Xe MAX Graphics round out the group at 14352 and 14315, respectively, with the Intel part trailing by 0.6%. This cluster is dominated by integrated graphics and older discrete parts, indicating the GTX 965M performance is close to that tier.

Looking at raw compute rates, the difference in FP32 is stark. The RTX PRO 6000 Blackwell achieves 126.0 TFLOPS FP32, while the GTX 965M reaches 1.946 TFLOPS. That is over 64 times more raw compute throughput. Pixel throughput follows: 502.5 GPixel/s for the newer card versus 30.40 GPixel/s for the older one. Texture rates are similarly lopsided at 1,968.0 GTexel/s versus 60.80 GTexel/s. Every one of these metrics favors the RTX PRO 6000 Blackwell by orders of magnitude, reflecting not just clock speed differences but also the massive increase in shaders, TMUs, and ROPs.

The memory bandwidth comparison is equally lopsided. At 1.79 TB/s, the RTX PRO 6000 Blackwell moves data at over 22 times the GTX 80. Once bandwidth is this far apart, workloads like high-resolution rendering, large model training, or multi-display output become feasible only on the newer card.

Where Each One Wins

The RTX PRO 6000 Blackwell wins in every measured category where both cards have data. It wins on memory capacity (96 GB at 1.79 TB/s vs 2 GB at 80.19 GB/s), on compute (126.0 TFLOPS vs 1.946 TFLOPS FP32), on pixel rate (502.5 GPixel/s vs 30.40 GPixel/s), and on texture rate (1,968.0 GTexel/s vs 60.80 GTexel/s). It also wins on modern feature support with DirectX 12 Ultimate, 188 RT cores, and 752 tensor cores, none of which exist on the GTX 965M.

The RTX PRO 6000 Blackwell is clearly positioned for professional workstation use. Its 96 GB memory pool and 512-bit bus support large datasets, and its 4x DisplayPort 2.1b outputs allow multi-monitor setups. It is an active product with a launch MSRP of 8,565 USD, and its closest competitor in the database, the AMD Radeon PRO W7500, scores nearly identically in the single shared benchmark type.

The GTX 965M has no benchmark category where it beats the RTX PRO 6000 Blackwell. Its wins are contextual: it is an MXM module, so it fits in notebooks, and it draws no dedicated power connectors, making it suitable for mobile systems. Its end-of-life status and 2015 release date mean it belongs to a different era of computing. For legacy laptop use, it remains functional, as its Geekbench OpenCL score of 14509 and Vulkan score of 14299 show it still performs near integrated graphics like the AMD Radeon RX Vega 11.

In practical terms, the RTX PRO 6000 Blackwell is the choice for anyone needing current workstation performance, large memory, and hardware ray tracing. The GTX 965M is the choice for someone maintaining or using an older mobile system where the MXM form factor and low power footprint are the deciding factors. The benchmark data does not suggest any workload where the GTX 965M would be preferred on performance grounds.