NVIDIA GeForce GTX 950M vs NVIDIA T600 Comparison

The Verdict

The data in this comparison is unambiguous. The NVIDIA T600 is the superior GPU by a wide margin in every recorded benchmark, despite the GeForce GTX 950M holding a slightly higher overall percentile ranking. In the two head-to-head tests available, the T600 wins both, with the GTX 950M trailing by 65% in Geekbench OpenCL and 74.5% in Geekbench Vulkan. The GTX 950M records zero wins against the T600.

For users selecting between these two, the choice depends on the workload. The T600, with its Turing architecture, 4 GB of GDDR6 memory, and 160.0 GB/s of bandwidth, is the clear pick for modern compute tasks and API-level performance. The GTX 950M, built on Maxwell with 4 GB of DDR3 memory and 28.80 GB/s of bandwidth, is an older mobile part that struggles to keep pace. The GTX 950M does sit at the 42nd percentile among all GPUs, which is higher than the T600's 39th percentile, but that ranking is based on a broader average of benchmarks that includes legacy tests. The recorded head-to-head data shows the T600 dominating where it matters most.

Choose the T600 for any workload that leverages OpenCL or Vulkan, as the delta is massive. Choose the GTX 950M only if the system requires a mobile-integrated form factor, as the slot width is listed as "IGP" and it draws 75 W, whereas the T600 is a single-slot card with a 40 W TDP that needs a 200 W suggested PSU. In raw performance, the T600 is the definitive winner.

Architecture Differences

The two GPUs come from different generations and process nodes. The GTX 950M uses the GM107 chip on a 28 nm process at TSMC, while the T600 uses the TU117 chip on a 12 nm process, also at TSMC. The transistor counts reflect the generational gap: the GTX 950M has 1,870 million transistors on a 148 mm² die, yielding a density of 12.6M per mm². The T600 packs 4,700 million transistors on a 200 mm² die, with a density of 23.5M per mm². The T600 nearly doubles the transistor count and nearly doubles the density, which explains its superior throughput.

Both cards have 640 shading units and 40 texture mapping units. The ROP count differs: the GTX 950M has 16 ROPs, while the T600 has 32 ROPs. This directly impacts pixel throughput. The GTX 950M delivers 17.98 GPixel/s, while the T600 delivers 42.72 GPixel/s. Texture rates also favor the T600: 53.40 GTexel/s versus 44.96 GTexel/s for the older card.

Memory architecture is a major split. The GTX 950M uses 4 GB of DDR3 on a 128-bit bus, running at 900 MHz with 1800 Mbps effective, for a bandwidth of 28.80 GB/s. The T600 uses 4 GB of GDDR6 on the same 128-bit bus, running at 1250 MHz with 10 Gbps effective, for a bandwidth of 160.0 GB/s. That is a 5.5x bandwidth advantage for the T600, which is critical for data-heavy workloads.

Clock behavior differs as well. The GTX 950M has a base clock of 993 MHz and a boost of 1124 MHz. The T600 has a lower base of 735 MHz but a much higher boost of 1335 MHz. The T600's boost clock is over 200 MHz higher than the GTX 950M's boost, which helps it maintain performance under load.

Feature support is another divide. The GTX 950M supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.4. The T600 supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The higher DirectX feature level on the T600 means better support for modern rendering paths. The T600 also has a PCIe 3.0 x16 interface, while the GTX 950M is limited to PCIe 3.0 x8, halving the available bus bandwidth for data transfers.

Power and physical design differ significantly. The GTX 950M has a TDP of 75 W and is listed as an IGP slot width with no power connectors. The T600 has a TDP of 40 W, is a single-slot card, also has no power connectors, but lists a suggested PSU of 200 W. The T600 is more power-efficient per unit of performance, and its display outputs are four mini-DisplayPort 1.4a connectors, while the GTX 950M's outputs are listed as portable device dependent.

Head-to-Head Benchmarks

The recorded head-to-head data shows a decisive sweep for the T600. In Geekbench OpenCL, the T600 scores 27,875 versus the GTX 950M's 9,745, a delta of 65% in favor of the T600. That is a 2.86x raw score advantage. The OpenCL result reflects the T600's superior memory bandwidth and newer architecture, which are both heavily exercised in compute workloads.

In Geekbench Vulkan, the margin is even wider. The T600 scores 25,580, while the GTX 950M scores 6,525, a delta of 74.5%. The T600 is 3.92x faster in this test. Vulkan is a low-level API that benefits from efficient scheduling and high bandwidth, and the T600's Turing architecture with GDDR6 memory provides both. The GTX 950M's DDR3 memory and Maxwell architecture are a clear bottleneck here.

The overall benchmark averages tell a similar story, though with less separation. The GTX 950M has an average benchmark score of 8,135, while the T600 has an average of 7,035. That puts the GTX 950M slightly ahead in the aggregate, but this is misleading. The GTX 950M's average is based on only two benchmarks (OpenCL and Vulkan), while the T600's average includes nine benchmarks, including several Passmark tests for DirectX 9, 10, 11, 12, G2D, G3D, and GPU compute. The T600's Passmark G3D score is 6,479, and its GPU compute score is 2,402, which are solid results. The GTX 950M has no recorded Passmark scores to compare.

The percentile rankings also diverge from the head-to-head results. The GTX 950M sits at the 42nd percentile among all GPUs, while the T600 sits at the 39th. However, the nearest rivals for each card show how close they are to their peer groups. The GTX 950M's closest rival is the AMD Radeon R9 M360 with an average score of 8,129 (a delta of 0.1%), and it is also within 0.7% of the NVIDIA GRID K2. The T600's closest rival is the NVIDIA GeForce GTX 680M with an average score of 7,023 (a delta of 0.2%), and it trails the GeForce GTX 970 by 1.7%. The T600's peer group is slightly lower in average score, but its peak performance in modern APIs is far higher than the GTX 950M's.

FAQ

Q: Which GPU has more memory bandwidth?

A: The NVIDIA T600 has significantly more memory bandwidth at 160.0 GB/s, compared to the GTX 950M's 28.80 GB/s. This is due to the T600's GDDR6 memory versus the GTX 950M's DDR3.

Q: Are both cards limited to the same DirectX support?

A: No. The T600 supports DirectX 12 (12_1), while the GTX 950M supports DirectX 12 (11_0). The T600 has a higher feature level.

Q: How do their power requirements compare?

A: The GTX 950M has a TDP of 75 W, while the T600 has a TDP of 40 W. The T600 also lists a suggested PSU of 200 W, while the GTX 950M has no suggested PSU listed.

Q: Which GPU wins in Geekbench Vulkan?

A: The NVIDIA T600 wins decisively, scoring 25,580 versus the GTX 950M's 6,525, a delta of 74.5% in favor of the T600.

Q: Do both cards have the same number of shading units?

A: Yes, both the GTX 950M and the T600 have 640 shading units and 40 TMUs. They differ in ROPs, with the T600 having 32 ROPs versus 16 on the GTX 950M.

Q: Which card has a higher boost clock?

A: The T600 has a higher boost clock at 1335 MHz, compared to the GTX 950M's 1124 MHz. The GTX 950M has a higher base clock at 993 MHz versus 735 MHz on the T600.

Where Each One Wins

The T600 wins in every recorded head-to-head benchmark, so the use-case split is heavily skewed. The T600 is the choice for any workload that depends on modern compute APIs. Its Geekbench OpenCL score of 27,875 and Vulkan score of 25,580 are both nearly four times higher than the GTX 950M's corresponding scores. The T600's GDDR6 memory, with 160.0 GB/s of bandwidth, makes it suitable for tasks that move large amounts of data, such as video processing, scientific compute, or any GPU-accelerated application that uses OpenCL.

The T600 also wins on feature support. Its DirectX 12 (12_1) feature level is higher than the GTX 950M's 11_0, so any game or application that relies on newer DirectX 12 features will run on the T600 but may be limited on the GTX 950M. The T600's PCIe 3.0 x16 interface provides double the bus bandwidth of the GTX 950M's x8 link, which matters for data transfer between the CPU and GPU.

The T600's pixel rate is 42.72 GPixel/s versus 17.98 GPixel/s on the GTX 950M, so the T600 is better for any task that involves high-resolution rendering or heavy pixel shading. Its texture rate of 53.40 GTexel/s also beats the GTX 950M's 44.96 GTexel/s.

The GTX 950M does have one niche: its form factor. It is listed as an IGP slot width, which means it is intended for integrated or portable systems. It also has a lower base clock but that does not translate to a performance win. The GTX 950M's average benchmark score of 8,135 is higher than the T600's 7,035, but that is due to the T600's inclusion of older Passmark DirectX tests where it scores very low (for example, 32 in DirectX 10 and 25 in DirectX 12). Those legacy scores drag down the T600's average, but they do not reflect its performance in modern workloads.

In summary, the T600 is the clear winner for compute, modern graphics APIs, and bandwidth-heavy tasks. The GTX 950M only retains relevance in older or less demanding scenarios where its lower power draw and integrated form factor might fit a specific portable design. For any user choosing between the two based on the recorded data, the T600 is the only rational pick.