NVIDIA T600 Mobile vs NVIDIA Tesla M60 Comparison

The NVIDIA T600 Mobile and NVIDIA Tesla M60 occupy very different positions in the GPU landscape, despite sharing a manufacturer. The T600 Mobile is a modern, low-power Turing-based mobile part, while the Tesla M60 is a high-power, dual-slot Maxwell-era accelerator designed for datacenter workloads. The benchmark data reveals a split decision: the T600 Mobile wins decisively in OpenCL, while the Tesla M60 edges ahead in Vulkan. This head-to-head analysis breaks down what those numbers mean, where each card excels, and who should choose which.

Head-to-Head Benchmarks

The two GPUs split their two benchmark comparisons, with the T600 Mobile taking the OpenCL test and the Tesla M60 taking the Vulkan test. In the Geekbench OpenCL benchmark, the T600 Mobile scores 35,486 points, while the Tesla M60 scores 29,506 points. This represents a 20.3% advantage for the T600 Mobile, a substantial margin that underscores the architectural efficiency of the newer Turing design. The T600 Mobile’s lead in OpenCL is its strongest showing, placing it comfortably ahead of its rival in compute workloads that leverage this API.

In contrast, the Geekbench Vulkan benchmark tells a different story. Here, the Tesla M60 scores 31,473 points, surpassing the T600 Mobile’s 30,211 points. The delta is 4% in favor of the Tesla M60, a narrower margin than the OpenCL gap but still a clear victory. This result indicates that the Maxwell architecture, despite its age, retains competitive performance in Vulkan-based scenarios. It is worth remembering the T600 Mobile’s Vulkan score is its weaker result, while the Tesla M60’s Vulkan score is its stronger one, suggesting a divergence in how each architecture handles these two APIs.

Looking at the broader competitive context, the T600 Mobile’s average benchmark score of 32,849 places it in the 77th percentile of all GPUs. This average is derived from its two benchmark results and positions it slightly above the NVIDIA P104-100, which has an average score of 32,982 (a 0.4% delta in favor of the P104-100), and above the AMD Radeon RX 590 GME at 32,601 (0.8% delta in favor of the T600 Mobile). The Tesla M60, with an average score of 30,490, sits in the 75th percentile. Its nearest rival, the NVIDIA CMP 70HX, scores 30,476, showing a negligible 0% delta, while the AMD Radeon RX 6700 trails at 30,433 (0.2% delta). These percentile rankings confirm that both cards are mid-to-upper tier performers, but the T600 Mobile holds a slight edge in average compute output across the two tests.

Where Each One Wins

The T600 Mobile’s 20.3% OpenCL victory makes it the clear choice for applications that rely heavily on OpenCL compute. This API is commonly used in scientific computing, image processing, and certain rendering tasks. With its Turing architecture and 2.527 TFLOPS of FP32 performance, the T600 Mobile demonstrates that modern instruction scheduling and cache design can overcome a significant deficit in raw shading unit count. Its 896 shading units, while fewer than the Tesla M60’s 2,048, are paired with a much higher boost clock of 1410 MHz compared to 1178 MHz on the Tesla M60, leading to more efficient execution per clock.

The Tesla M60, on the other hand, wins the Vulkan workload by 4%. Vulkan is a low-overhead API often used in gaming and real-time graphics, but also in compute-heavy professional applications. The Tesla M60’s victory here is notable given its lower base clock of 557 MHz and lower boost clock of 1178 MHz. Its advantage lies in its sheer scale: 2,048 shading units, 128 texture mapping units, and 64 render output units. This hardware parallelism allows it to push through Vulkan’s draw calls and compute dispatches more effectively than the smaller T600 Mobile. The Tesla M60 also offers double the memory capacity at 8 GB versus 4 GB, though its memory bandwidth is lower at 160.4 GB/s compared to 192.0 GB/s on the T600 Mobile.

In terms of pixel and texture throughput, the Tesla M60 dominates on paper, with a pixel rate of 75.39 GPixel/s and a texture rate of 150.8 GTexel/s, versus 45.12 GPixel/s and 78.96 GTexel/s for the T600 Mobile. These figures suggest that the Tesla M60 is better suited for rasterization-heavy tasks, even if the T600 Mobile’s architecture is more efficient per watt. The T600 Mobile’s FP16 performance of 5.053 TFLOPS (2:1) is a distinct advantage where half-precision compute is usable, a feature entirely absent from the Tesla M60, which lists no FP16 capability.

Architecture Differences

The two GPUs are built on fundamentally different architectures and process nodes. The T600 Mobile uses the TU117 chip based on the Turing architecture, manufactured on a 12 nm process at TSMC. This chip contains 4,700 million transistors on a die size of 200 mm², yielding a transistor density of 23.5 million per mm². The Tesla M60, by contrast, uses the GM204 chip based on the Maxwell 2.0 architecture, also fabricated by TSMC but on an older 28 nm process. This chip packs 5,200 million transistors into a much larger 398 mm² die, resulting in a lower transistor density of 13.1 million per mm². The smaller, denser Turing chip benefits from architectural improvements that maximize performance per transistor.

Clock speeds differ significantly. The T600 Mobile has a base clock of 780 MHz and a boost clock of 1410 MHz, while the Tesla M60 runs at 557 MHz base and 1178 MHz boost. The T600 Mobile’s higher clocks are a direct result of the more efficient 12 nm process and lower power envelope. Memory configurations also diverge: the T600 Mobile uses 4 GB of GDDR6 memory on a 128-bit bus, achieving 192.0 GB/s of bandwidth, with an effective speed of 12 Gbps. The Tesla M60 uses 8 GB of GDDR5 memory on a 256-bit bus, but its effective speed of 5 Gbps yields only 160.4 GB/s of bandwidth. The T600 Mobile’s newer memory technology provides higher bandwidth despite a narrower bus.

Power and physical design could not be more different. The T600 Mobile has a TDP of 40 W, is integrated into the system (IGP form factor), requires no power connectors, and has no display outputs beyond being portable device dependent. The Tesla M60, on the other hand, has a TDP of 300 W, occupies a dual-slot form factor, requires a single 8-pin power connector, and suggests a 700 W power supply. It measures 267 mm (10.5 inches) in length and has no display outputs whatsoever, being a compute-only accelerator. The Tesla M60 is also an older product, released in August 2015, while the T600 Mobile is from April 2021. Both are end-of-life products, but the T600 Mobile is significantly newer.

In terms of API support, both cards support DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. Neither has ray tracing cores or tensor cores, so those features are absent from both. The T600 Mobile’s generation is listed as Quadro Turing-M (Tx000), while the Tesla M60 is from the Tesla Maxwell (Mxx) generation. The T600 Mobile’s predecessor is Quadro Pascal-M, with a successor of Ampere-MW, while the Tesla M60’s predecessor is Tesla Kepler and its successor is Tesla Pascal.

The Verdict

The data presents a clear trade-off between these two GPUs. For users prioritizing OpenCL compute performance, the T600 Mobile is the superior choice, offering a 20.3% higher score in that benchmark. Its modern Turing architecture, higher clocks, and efficient 12 nm process deliver better raw compute in that API. Additionally, its 40 W power draw and integrated form factor make it suitable for mobile workstations or compact systems where power and space are at a premium. The T600 Mobile’s 77th percentile ranking also places it slightly higher than the Tesla M60’s 75th percentile in overall performance.

For scenarios where Vulkan is the primary API, the Tesla M60 holds a 4% advantage. This makes it a viable option for workloads that are optimized for Vulkan, particularly those that can leverage its massive parallel throughput from 2,048 shading units and 64 ROPs. The Tesla M60’s 8 GB memory capacity is double that of the T600 Mobile, which could be a deciding factor for datasets that exceed 4 GB. However, the Tesla M60’s 300 W power draw, dual-slot size, and requirement for a 700 W power supply make it impractical for most mobile or low-power deployments.

Strictly from the benchmark data, the T600 Mobile is the better all-around performer, with a higher average score of 32,849 versus 30,490 for the Tesla M60. It also wins the more demanding OpenCL test by a wide margin. The Tesla M60’s Vulkan victory is notable but narrow, and its architectural age shows in its lower clock speeds and older memory standard. Unless a specific workload relies on Vulkan and requires more than 4 GB of memory, the T600 Mobile is the more capable GPU. The Tesla M60’s only clear advantages are memory capacity and Vulkan-specific performance, which are niche requirements in the current landscape.

FAQ

Q: Which GPU has a higher average benchmark score?

A: The NVIDIA T600 Mobile has a higher average benchmark score of 32,849, compared to the NVIDIA Tesla M60’s average of 30,490.

Q: What is the performance difference in the Geekbench OpenCL test?

A: The T600 Mobile scores 35,486, which is 20.3% higher than the Tesla M60’s score of 29,506 in the Geekbench OpenCL benchmark.

Q: Does the Tesla M60 win any benchmark against the T600 Mobile?

A: Yes, the Tesla M60 wins the Geekbench Vulkan benchmark with a score of 31,473, which is 4% higher than the T600 Mobile’s score of 30,211.

Q: What are the memory capacities of each GPU?

A: The T600 Mobile has 4 GB of GDDR6 memory, while the Tesla M60 has 8 GB of GDDR5 memory.

Q: How do the power requirements differ between the two cards?

A: The T600 Mobile has a TDP of 40 W and requires no power connectors, while the Tesla M60 has a TDP of 300 W, requires a single 8-pin power connector, and suggests a 700 W power supply.

Q: Are both GPUs compatible with the same graphics APIs?

A: Yes, both the T600 Mobile and the Tesla M60 support DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. Neither supports ray tracing or tensor cores.