GPU Comparison

# NVIDIA GRID M60-1Q vs NVIDIA Tesla M60

Both cards share the same GM204 silicon, the same 28 nm TSMC process, and the same Maxwell 2.0 architecture. The GRID M60-1Q ships with 1 GB of GDDR5 memory, while the Tesla M60 carries 8 GB. In the only directly comparable benchmark, the Geekbench Vulkan test, the Tesla M60 scores 31,473 against the GRID M60-1Q's 31,220, a delta of -0.8% in favor of the Tesla. The GRID M60-1Q sits at the 76th percentile of all GPUs, while the Tesla M60 sits at the 75th. Average benchmark scores are 31,220 for the GRID and 30,490 for the Tesla, though the Tesla's average includes an additional OpenCL result of 29,506. Neither card has display outputs, both are dual-slot, and both use a single 8-pin power connector. The Tesla M60 carries a 300 W TDP and a 700 W suggested PSU, while the GRID M60-1Q draws 225 W and suggests a 550 W PSU. Both are end-of-life products released on the same date.

FAQ

Q: Which card is faster in Vulkan benchmarking?

A: The Tesla M60 wins the Geekbench Vulkan test with a score of 31,473, edging out the GRID M60-1Q's 31,220. The margin is 0.8%, effectively a statistical tie given the shared silicon.

Q: Do the two cards have the same memory bandwidth?

A: Yes. Both feature a 256-bit memory bus with GDDR5 memory running at 1253 MHz (5 Gbps effective), producing an identical 160.4 GB/s of bandwidth.

Q: What is the memory capacity difference?

A: The GRID M60-1Q has 1 GB of GDDR5, while the Tesla M60 has 8 GB of GDDR5. This is the single largest specification gap between the two boards.

Q: How do these cards compare to their nearest rivals?

A: The GRID M60-1Q's Vulkan score of 31,220 is within 0.4% of the GeForce RTX 4070 Ti SUPER (31,087) and within 1% of the RTX PRO 4500 Blackwell (31,532). The Tesla M60's average score of 30,490 places it 1.8% ahead of the GeForce RTX 3070 Ti (29,945) and 1.3% ahead of the Radeon RX 6800 (30,095).

Q: What are the power requirements?

A: The GRID M60-1Q has a 225 W TDP with a suggested 550 W PSU. The Tesla M60 has a 300 W TDP with a suggested 700 W PSU. Both use a single 8-pin power connector.

Q: Are these cards still in production?

A: No. Both are marked as end-of-life. They were released on the same date, and the Tesla M60's predecessor is Tesla Kepler with a successor of Tesla Pascal. The GRID M60-1Q lists no predecessor or successor.

Architecture Differences

Both cards are built on the GM204 chip using the Maxwell 2.0 architecture, fabricated at TSMC on a 28 nm process. The die size is identical at 398 mm², and the transistor count is the same at 5,200 million, yielding a transistor density of 13.1 million per square millimeter. Shading units are 2,048 on both, with 128 texture mapping units and 64 ROPs. Pixel rate is 75.39 GPixel/s, texture rate is 150.8 GTexel/s, and FP32 throughput is 4.825 TFLOPS on both cards. Neither card has RT cores or tensor cores, and FP16 performance is not listed for either.

The clocks are identical: 557 MHz base, 1178 MHz boost, and 1253 MHz memory (5 Gbps effective). The bus interface is PCIe 3.0 x16 on both. API support matches as well, with DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. Physical dimensions are the same, 267 mm (10.5 inches) in length, dual-slot width.

The architectural differences are limited to memory capacity (1 GB vs 8 GB), TDP (225 W vs 300 W), suggested PSU (550 W vs 700 W), and generation naming. The GRID M60-1Q belongs to the GRID (Mx) generation, while the Tesla M60 belongs to the Tesla Maxwell (Mxx) generation. The Tesla M60 also has documented lineage with Tesla Kepler as predecessor and Tesla Pascal as successor, whereas the GRID M60-1Q has no listed predecessors or successors.

Head-to-Head Benchmarks

The only direct head-to-head benchmark available is Geekbench Vulkan. The Tesla M60 scores 31,473, and the GRID M60-1Q scores 31,220. The Tesla wins by 0.8%, which is a narrow margin given that both cards share identical clocks, shader counts, and memory bandwidth. The delta of -0.8% for the GRID M60-1Q suggests run-to-run variance rather than a fundamental performance difference.

Looking at the broader competitive landscape, the GRID M60-1Q's Vulkan score of 31,220 places it 0.4% above the GeForce RTX 4070 Ti SUPER (31,087) and 1% below the RTX PRO 4500 Blackwell (31,532). It is also 1.4% below the TITAN RTX (31,676). The nearest rival, the Quadro M5000, scores 31,206, a 0% delta, meaning the GRID M60-1Q and Quadro M5000 are effectively tied.

The Tesla M60's average benchmark score of 30,490 is based on two results: the Vulkan score of 31,473 and an OpenCL score of 29,506. Its nearest rival, the CMP 70HX, averages 30,476, a 0% delta. The Tesla M60 sits 0.2% above the Radeon RX 6700 (30,433), 1.3% above the Radeon RX 6800 (30,095), and 1.8% above the GeForce RTX 3070 Ti (29,945).

The headline is that these two cards are performance twins in compute workloads. The Vulkan score difference of 253 points (31,473 vs 31,220) is less than the gap between the GRID M60-1Q and its nearest rival, the Quadro M5000, which differs by only 14 points. The Tesla M60's OpenCL result of 29,506 is notably lower than its Vulkan score, suggesting API-dependent scaling that the GRID M60-1Q does not have a comparable data point for.

The Verdict

From the data, the Tesla M60 is the marginally faster card in Vulkan, winning the only head-to-head benchmark by 0.8%. It also offers 8 GB of memory versus the GRID M60-1Q's 1 GB, which is a substantial capacity advantage for workloads that exceed 1 GB of frame buffer. The Tesla M60's average benchmark score of 30,490 is lower than the GRID M60-1Q's 31,220, but that is because the Tesla's average includes the OpenCL result of 29,506, which drags it down.

The GRID M60-1Q has a lower TDP of 225 W versus 300 W, and a suggested PSU of 550 W versus 700 W. For systems with power constraints, the GRID M60-1Q is the more efficient choice. Both cards are end-of-life, so neither is a forward-looking purchase. The Tesla M60 has a clear lineage (Tesla Kepler predecessor, Tesla Pascal successor), while the GRID M60-1Q does not.

For compute workloads that fit within 1 GB of memory, the GRID M60-1Q and Tesla M60 are functionally equivalent in raw throughput. The 0.8% Vulkan delta is negligible. For workloads that need more than 1 GB, the Tesla M60 is the only option between the two. The Tesla M60's 8 GB frame buffer is the decisive differentiator in this comparison.

The GRID M60-1Q's percentile ranking of 76 versus the Tesla M60's 75 is within noise, and both cards sit in the same performance tier as modern GPUs like the RTX 4070 Ti SUPER and RTX 3070 Ti. Neither card has display outputs, making both unsuitable for desktop use without a secondary GPU.

Given the data, the Tesla M60 is the stronger choice for memory-intensive tasks and offers a slight performance edge in Vulkan. The GRID M60-1Q is the better pick for power-constrained environments where 1 GB of memory suffices. Both cards are end-of-life, so the decision hinges on memory capacity and power budget rather than generational features.

Specification Differences

| Field | NVIDIA GRID M60-1Q | NVIDIA Tesla M60 |

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

| Generation | GRID (Mx) | Tesla Maxwell (Mxx) |

| Memory Size | 1024 MB (1 GB) | 8 GB |

| TDP | 225 W | 300 W |

| Suggested PSU | 550 W | 700 W |

| Predecessor | None listed | Tesla Kepler |

| Successor | None listed | Tesla Pascal |

| Geekbench Vulkan Score | 31,220 | 31,473 |

| Geekbench OpenCL Score | Not listed | 29,506 |

| Average Benchmark Score | 31,220 | 30,490 |

| Percentile vs All GPUs | 76 | 75 |

| Nearest Rival | Quadro M5000 (31,206, 0%) | CMP 70HX (30,476, 0%) |

All other fields are identical: GM204 chip, Maxwell 2.0 architecture, 28 nm process, 5,200 million transistors, 398 mm² die size, 13.1M/mm² transistor density, 557 MHz base clock, 1178 MHz boost clock, 1253 MHz memory clock (5 Gbps effective), 160.4 GB/s bandwidth, 2048 shading units, 128 TMUs, 64 ROPs, 75.39 GPixel/s pixel rate, 150.8 GTexel/s texture rate, 4.825 TFLOPS FP32, dual-slot width, 1x 8-pin power connector, PCIe 3.0 x16 bus interface, no display outputs, DirectX 12 (12_1), OpenGL 4.6, Vulkan 1.4, 267 mm length, and end-of-life production status.