NVIDIA GeForce RTX 3080 Ti Mobile vs NVIDIA Tesla M60 Comparison

The NVIDIA Tesla M60 and the NVIDIA GeForce RTX 3080 Ti Mobile occupy opposite ends of the GPU spectrum, both chronologically and architecturally. The Tesla M60, a Maxwell-based accelerator from 2015, was built for datacenter workloads, while the RTX 3080 Ti Mobile, an Ampere part from 2022, targets high-end laptops. Despite their different purposes, the benchmark data reveals a clear performance hierarchy, with the mobile chip dominating in every recorded test. This analysis breaks down where each card wins, what separates them internally, and what the numbers mean for potential users.

Where Each One Wins

The recorded benchmarks show a complete sweep for the RTX 3080 Ti Mobile. In both head-to-head tests, the OpenCL and Vulkan workloads, the mobile Ampere GPU outperforms the Tesla M60 by a wide margin. The Tesla M60 does not secure a single win in any direct comparison. However, the Tesla M60 still holds relevance in its niche. Its design as a dual-slot, 300-watt accelerator with no display outputs indicates a clear focus on server-side compute, not interactive graphics. The RTX 3080 Ti Mobile, by contrast, is a portable device-dependent part, meaning its outputs and power delivery rely on the host laptop.

The data suggests that the Tesla M60’s strengths lie in its intended environment: sustained, power-hungry compute tasks in a rack server, where its 300-watt TDP is acceptable and its lack of display outputs is irrelevant. The RTX 3080 Ti Mobile wins on raw performance and efficiency, as evidenced by its 115-watt TDP and far higher scores. For any task that involves OpenCL or Vulkan, the mobile chip is the clear winner. For legacy datacenter deployments where Maxwell-era compatibility matters, the Tesla M60 remains a functional, if outdated, option.

Architecture Differences

The two GPUs come from different architectural eras and manufacturing processes. The Tesla M60 uses the GM204 chip, built on Maxwell 2.0 architecture, fabricated on a 28 nm process at TSMC. It packs 5,200 million transistors into a 398 mm² die, yielding a transistor density of 13.1 million per square millimeter. In contrast, the RTX 3080 Ti Mobile uses the GA103 chip, based on Ampere architecture, manufactured on Samsung’s 8 nm process. This newer node allows for 22,000 million transistors on a 496 mm² die, a density of 44.4 million per square millimeter, more than three times that of the Maxwell chip.

Memory configurations differ significantly. The Tesla M60 features 8 GB of GDDR5 on a 256-bit bus, with a memory clock of 1253 MHz (5 Gbps effective) and bandwidth of 160.4 GB/s. The RTX 3080 Ti Mobile doubles the capacity to 16 GB of GDDR6, also on a 256-bit bus, but with a memory clock of 2000 MHz (16 Gbps effective), delivering 512.0 GB/s of bandwidth, more than three times the Tesla’s throughput.

Compute resources also show a generational leap. The Tesla M60 has 2048 shading units, 128 texture mapping units, and 64 ROPs. The RTX 3080 Ti Mobile has 7424 shading units, 232 TMUs, and 96 ROPs. The Ampere chip also introduces dedicated hardware absent from Maxwell: 58 ray tracing cores and 232 tensor cores. The Tesla M60 has no equivalent for these features. The pixel rate for the Tesla M60 is 75.39 GPixel/s, while the RTX 3080 Ti Mobile reaches 121.0 GPixel/s. Texture rates are 150.8 GTexel/s versus 292.3 GTexel/s, respectively.

Clock speeds tell a nuanced story. The Tesla M60 has a base clock of 557 MHz and a boost of 1178 MHz. The RTX 3080 Ti Mobile has a higher base of 810 MHz and a boost of 1260 MHz. Despite the modest clock advantage, the massive difference in shading units and memory bandwidth explains the performance gap.

Head-to-Head Benchmarks

The direct comparison in the database includes two tests: Geekbench OpenCL and Geekbench Vulkan. Both show overwhelming wins for the RTX 3080 Ti Mobile.

In Geekbench OpenCL, the Tesla M60 scores 29,506, while the RTX 3080 Ti Mobile scores 117,866. The delta is negative 75 percent from the perspective of the Tesla M60, meaning the mobile chip is roughly four times faster in this compute workload. This aligns with the FP32 throughput numbers: the Tesla M60 delivers 4.825 TFLOPS, while the RTX 3080 Ti Mobile reaches 18.71 TFLOPS, a 3.9x advantage.

In Geekbench Vulkan, the Tesla M60 scores 31,473, and the RTX 3080 Ti Mobile scores 107,502. The delta is negative 70.7 percent, indicating the mobile chip is about 3.4 times faster. Vulkan is a lower-level API that can expose architectural differences. The RTX 3080 Ti Mobile’s higher shading unit count and faster memory likely drive this result. The Tesla M60’s Maxwell architecture supports Vulkan 1.4, as does Ampere, so API compatibility is not the differentiator.

The RTX 3080 Ti Mobile also has additional benchmark entries not recorded for the Tesla M60, including 3DMark Steel Nomad DX12 (2,869), Passmark DX10 (131), DX11 (164), DX12 (88), DX9 (201), G2D (818), G3D (19,288), and GPU compute (8,471). These scores provide context for its overall average benchmark score of 25,740, compared to the Tesla M60’s 30,490 average. Interestingly, the Tesla M60 has a higher average score despite losing both head-to-head tests, because the RTX 3080 Ti Mobile’s average includes many lower-scoring Passmark tests that drag its mean down. This illustrates why average scores alone can be misleading; the direct head-to-head results are more informative.

FAQ

Q: Which GPU has a higher average benchmark score?

A: The Tesla M60 has an average benchmark score of 30,490, while the RTX 3080 Ti Mobile averages 25,740. However, this average includes different test sets; in the two direct head-to-head tests (OpenCL and Vulkan), the RTX 3080 Ti Mobile wins decisively.

Q: How much faster is the RTX 3080 Ti Mobile in OpenCL?

A: The RTX 3080 Ti Mobile scores 117,866 in Geekbench OpenCL, compared to the Tesla M60’s 29,506. This represents a 75 percent lower score for the Tesla, meaning the mobile chip is about four times faster.

Q: What is the memory capacity difference?

A: The Tesla M60 has 8 GB of GDDR5, while the RTX 3080 Ti Mobile has 16 GB of GDDR6. Both use a 256-bit bus, but the mobile GPU’s memory runs at 16 Gbps effective versus 5 Gbps effective, yielding 512.0 GB/s versus 160.4 GB/s bandwidth.

Q: Does the RTX 3080 Ti Mobile support ray tracing?

A: Yes, the RTX 3080 Ti Mobile includes 58 ray tracing cores and 232 tensor cores. The Tesla M60 has no ray tracing or tensor core hardware, as Maxwell predates those features.

Q: Which GPU has a lower power draw?

A: The RTX 3080 Ti Mobile has a TDP of 115 watts, while the Tesla M60 has a TDP of 300 watts. The mobile chip achieves far higher performance with less than half the power budget.

Q: Are both GPUs end-of-life?

A: Yes, both are listed as end-of-life. The Tesla M60 was released in August 2015, and the RTX 3080 Ti Mobile was released in January 2022.

The Verdict

The data is unambiguous. For any workload captured in the benchmark suite, the RTX 3080 Ti Mobile is the superior GPU. Its OpenCL score is 117,866 versus 29,506, and its Vulkan score is 107,502 versus 31,473. The mobile chip also has three times the memory bandwidth, nearly four times the FP32 throughput, and a much higher shading unit count. The Tesla M60’s only advantages are its legacy status for Maxwell-compatible datacenter environments and its higher average benchmark score, which is an artifact of different test sets.

Who should pick the Tesla M60? Only those maintaining existing infrastructure that requires a 2015-era Maxwell accelerator with a 300-watt TDP, dual-slot form factor, and no display outputs. Its PCIe 3.0 x16 interface and 8 GB GDDR5 memory are sufficient for older compute workloads but cannot match modern demands. The RTX 3080 Ti Mobile, despite being a laptop part, outperforms it across the board.

Who should pick the RTX 3080 Ti Mobile? Anyone needing high compute performance in a portable package. Its 115-watt TDP, 16 GB GDDR6 memory, and PCIe 4.0 x16 interface make it a far more capable and efficient option. The ray tracing cores and tensor cores open up modern graphics and AI workloads that the Tesla M60 cannot handle. The benchmark results show a generational leap in compute capability, making the mobile chip the obvious choice for new deployments.

Specification Differences

| Specification | NVIDIA Tesla M60 | NVIDIA GeForce RTX 3080 Ti Mobile |

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

| Chip | GM204 | GA103 |

| Architecture | Maxwell 2.0 | Ampere |

| Generation | Tesla Maxwell (Mxx) | GeForce 30 Mobile |

| Process Node | 28 nm (TSMC) | 8 nm (Samsung) |

| Transistors | 5,200 million | 22,000 million |

| Die Size | 398 mm² | 496 mm² |

| Transistor Density | 13.1M / mm² | 44.4M / mm² |

| Base Clock | 557 MHz | 810 MHz |

| Boost Clock | 1178 MHz | 1260 MHz |

| Memory Clock | 1253 MHz (5 Gbps effective) | 2000 MHz (16 Gbps effective) |

| Memory Size | 8 GB GDDR5 | 16 GB GDDR6 |

| Memory Bandwidth | 160.4 GB/s | 512.0 GB/s |

| Shading Units | 2048 | 7424 |

| TMUs | 128 | 232 |

| ROPs | 64 | 96 |

| RT Cores | None | 58 |

| Tensor Cores | None | 232 |

| Pixel Rate | 75.39 GPixel/s | 121.0 GPixel/s |

| Texture Rate | 150.8 GTexel/s | 292.3 GTexel/s |

| FP32 | 4.825 TFLOPS | 18.71 TFLOPS |

| FP16 | Not listed | 18.71 TFLOPS (1:1) |

| TDP | 300 W | 115 W |

| Bus Interface | PCIe 3.0 x16 | PCIe 4.0 x16 |

| Display Outputs | No outputs | Portable Device Dependent |

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

| Release Date | 2015-08-29 | 2022-01-24 |

| Predecessor | Tesla Kepler | GeForce 20 Mobile |

| Successor | Tesla Pascal | Not listed |