NVIDIA GRID M60-1Q vs NVIDIA Quadro GV100 Comparison

Where Each One Wins

The benchmark data splits cleanly between these two professional NVIDIA workstation cards, but the comparison is heavily lopsided. The NVIDIA Quadro GV100 records wins in every recorded head-to-head test, with the sole shared benchmark being Geekbench Vulkan, where it posts a score of 139,526 against the GRID M60-1Q's 31,220. That is a 346.9% advantage, a gap so large that the two cards are effectively in different performance tiers.

The GRID M60-1Q, however, is not without its own domain. The database shows only one benchmark result for this card, Geekbench Vulkan, so its strengths must be inferred from its architecture and positioning rather than from a broad benchmark suite. The card belongs to the GRID generation, which targets virtualized graphics workloads. It has no display outputs, which means it is designed for server-side rendering and remote desktop acceleration rather than direct workstation use. The Quadro GV100, by contrast, has four DisplayPort 1.4a outputs and is built for physical workstation deployment.

For use cases involving local rendering, compute workloads, or high-resolution display output, the Quadro GV100 is the clear choice based on the recorded data. For virtual desktop infrastructure or cloud gaming scenarios where the card sits inside a server and streams frames to clients, the GRID M60-1Q's design goals align with that specific task, even if its raw score in the one shared test is far lower. The data shows the GV100 wins the performance comparison outright, but the GRID card occupies a niche where raw benchmark scores matter less than virtualization features and power efficiency per user session.

FAQ

Q: Which card has the higher average benchmark score?

A: The NVIDIA Quadro GV100 has an average benchmark score of 35,520 across all its recorded tests, while the NVIDIA GRID M60-1Q has an average of 31,220 from its single Geekbench Vulkan result. The GV100 also sits at the 80th percentile among all GPUs, compared to the GRID card's 76th percentile.

Q: How do the two cards compare in the shared Geekbench Vulkan test?

A: The Quadro GV100 scores 139,526 in Geekbench Vulkan, while the GRID M60-1Q scores 31,220. The GV100 wins by 346.9%, which is the only head-to-head benchmark recorded in the database.

Q: What memory configurations do these cards use?

A: The Quadro GV100 uses 32 GB of HBM2 memory on a 4096-bit bus, delivering 868.4 GB/s of bandwidth. The GRID M60-1Q uses 1024 MB of GDDR5 memory on a 256-bit bus, providing 160.4 GB/s of bandwidth. The GV100 has 32 times the capacity and more than five times the bandwidth.

Q: Are both cards still in production?

A: No. Both are listed as end-of-life products. The Quadro GV100 was released on 2018-03-26, and the GRID M60-1Q was released on 2015-08-29. The GV100 has a successor in Quadro Turing, while the GRID card has no recorded successor.

Q: Do these cards support the same graphics APIs?

A: Yes. Both support DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The Quadro GV100 adds compute capabilities through its tensor cores, which the GRID card lacks entirely.

Q: What is the physical size difference?

A: Both cards are dual-slot designs with a length of 267 mm (10.5 inches). The Quadro GV100 has a recorded height of 111 mm (4.4 inches), while the GRID M60-1Q's height is not listed in the database.

Head-to-Head Benchmarks

The database records exactly one shared benchmark between these two cards: Geekbench Vulkan. The results are stark. The Quadro GV100 produces a score of 139,526, while the GRID M60-1Q manages 31,220. The delta is 346.9%, meaning the GV100 delivers roughly four and a half times the Vulkan performance of the GRID card. This is not a marginal difference; it represents a complete generational and architectural leap.

The GV100's other benchmark results, while not directly comparable to the GRID card (which lacks those specific tests), give context for its overall capability. In Geekbench OpenCL, it scores 150,004, which is even higher than its Vulkan result. In Passmark G3D, it posts 19,650, and in Passmark GPU Compute, it records 9,069. The legacy DirectX tests show scores of 207 for DirectX 9, 168 for DirectX 11, 140 for DirectX 10, and 84 for DirectX 12. The G2D test yields 836.

The GRID M60-1Q has no such breadth of recorded data. Its single Vulkan score of 31,220 places it near the NVIDIA Quadro M5000 (31,206, a 0% delta) and slightly below the NVIDIA TITAN RTX (31,676, a -1.4% delta). The GV100's nearest rivals, meanwhile, are the NVIDIA GeForce RTX 5070 Ti Mobile (35,435, a 0.2% delta), AMD Radeon Pro Duo (35,860, a -0.9% delta), NVIDIA T1000 (36,289, a -2.1% delta), and NVIDIA A2 (34,690, a 2.4% delta). This places the GV100 in a performance bracket with modern midrange-to-high-end cards, while the GRID M60-1Q sits alongside older Maxwell-era workstations.

The 346.9% Vulkan gap is the single most important number in this comparison. It shows that the GV100 is not merely faster but categorically superior in compute-heavy graphics workloads. The GRID card's design goals, however, emphasize multi-user virtualization rather than peak single-GPU performance, which explains why its raw score is so much lower.

Specification Differences

The two cards differ across nearly every major specification category. Process node: the GV100 uses a 12 nm process from TSMC, while the GRID M60-1Q uses a 28 nm process from the same foundry. Transistor count: the GV100 has 21,100 million transistors on an 815 mm² die, versus 5,200 million on a 398 mm² die for the GRID card. Transistor density follows: 25.9M per mm² for the GV100, 13.1M per mm² for the GRID.

Clock speeds: the GV100 runs at a base of 1132 MHz and boosts to 1627 MHz. The GRID card runs at 557 MHz base and 1178 MHz boost. Memory clocks differ as well: the GV100's HBM2 runs at 848 MHz (1696 Mbps effective), while the GRID's GDDR5 runs at 1253 MHz (5 Gbps effective).

Memory capacity is a major differentiator: 32 GB on the GV100 versus 1024 MB on the GRID card. Bus width: 4096 bits versus 256 bits. Bandwidth: 868.4 GB/s versus 160.4 GB/s.

Compute resources: the GV100 has 5,120 shading units, 320 TMUs, 128 ROPs, and 640 tensor cores. The GRID card has 2,048 shading units, 128 TMUs, and 64 ROPs, with no tensor cores. Pixel rate: 208.3 GPixel/s versus 75.39 GPixel/s. Texture rate: 520.6 GTexel/s versus 150.8 GTexel/s. FP32 throughput: 16.66 TFLOPS versus 4.825 TFLOPS. The GV100 also supports FP16 at 33.32 TFLOPS (2:1 ratio), while the GRID card has no recorded FP16 capability.

Power draw: the GV100 is rated at 250 W TDP with a suggested 600 W PSU, while the GRID card draws 225 W with a suggested 550 W PSU. Both use a single 8-pin power connector and are dual-slot designs. Display outputs differ completely: the GV100 has 4x DisplayPort 1.4a, while the GRID card has no outputs at all.

Architecture Differences

The Quadro GV100 is built on the Volta architecture, while the GRID M60-1Q uses Maxwell 2.0. This is a two-generation leap in NVIDIA's design philosophy. Volta introduced tensor cores, which the GV100 implements with 640 units, enabling accelerated AI and deep learning workloads. The Maxwell 2.0 architecture in the GRID card has no tensor core support, meaning no hardware acceleration for neural network inference or training.

The GV100 uses a 12 nm process with a massive 815 mm² die and 21,100 million transistors. The GRID card uses a 28 nm process with a 398 mm² die and 5,200 million transistors. The Volta design also brings HBM2 memory, which offers far higher bandwidth and capacity than the GDDR5 used by the GRID card. The 4096-bit memory bus on the GV100 is unprecedented in this comparison, enabling 868.4 GB/s of throughput.

The GRID M60-1Q belongs to the GRID (Mx) generation, which is specifically designed for virtualized environments. Its lack of display outputs confirms this: it is meant to be installed in servers and accessed remotely. The Maxwell 2.0 architecture supports virtualization features that were advanced for its time, but it lacks the compute-focused additions of Volta. The GV100's architecture, with its tensor cores and higher FP32 throughput, is better suited for scientific computing, simulation, and AI research. The GRID card's architecture is optimized for streaming multiple virtual desktops from a single physical card.

Architecture also affects efficiency. The GV100 achieves 25.9M transistors per mm² on 12 nm, versus 13.1M on 28 nm for the GRID card. This density improvement allows the GV100 to deliver 16.66 TFLOPS FP32 while drawing only 25 W more power than the GRID card's 4.825 TFLOPS. The per-watt performance difference is substantial, even if the raw power draw is similar.

The Verdict

The data supports a clear split based on workload type. For any task involving local graphics rendering, compute, AI, or high-bandwidth memory access, the NVIDIA Quadro GV100 is the superior choice. Its 346.9% lead in Geekbench Vulkan over the GRID M60-1Q is decisive. Its 32 GB of HBM2 memory, 640 tensor cores, and 16.66 TFLOPS FP32 throughput put it in a different performance class. The GV100 also has display outputs, making it suitable for direct workstation use. Its average benchmark score of 35,520 and 80th percentile ranking confirm it as a high-end professional card.

The NVIDIA GRID M60-1Q is a specialized tool for virtualized graphics. Its single recorded Vulkan score of 31,220 places it at the 76th percentile, close to the Quadro M5000 and TITAN RTX in terms of aggregate score. But its design tells a different story: no display outputs, 225 W TDP, and Maxwell 2.0 architecture optimized for multi-user server deployments. For organizations running virtual desktop infrastructure, the GRID card's strengths lie in its virtualization capabilities, not its raw benchmark performance. Its 1024 MB memory capacity is severely limited compared to the GV100, but in a virtualized environment, each user session might consume only a fraction of that memory.

The verdict depends entirely on the deployment scenario. If the requirement is maximum single-GPU performance in a physical workstation or a compute server, the Quadro GV100 wins without contest. If the requirement is serving multiple virtual desktop sessions from a single card, the GRID M60-1Q is architecturally designed for that purpose, though its benchmark scores suggest it cannot compete with the GV100 on raw speed. The recorded data shows one winner in every shared test, but the GRID card's lack of display outputs and server-oriented design mean it was never intended to compete in the same arena. Choose the GV100 for performance, the GRID card for virtualized multi-user deployments.