GPU Comparison

The Verdict

The data presents a clear split: the NVIDIA T600 is the superior choice for compute-oriented workloads, while the GTX 880M retains relevance only in specific legacy scenarios. The T600 wins the only direct head-to-head benchmark in the database, the Geekbench OpenCL test, by a massive margin. Its score of 27,875 versus the 880M's 5,622 represents a 79.8% deficit for the older card. If your priority is raw compute throughput, the T600 is the only rational pick from the recorded data.

The GTX 880M, however, is not without merit. It carries twice the memory capacity (8 GB versus 4 GB) and a wider 256-bit memory bus, which can matter for certain large-frame-buffer workloads. But the benchmark evidence is overwhelmingly one-sided. The T600 also posts a higher percentile ranking among all GPUs in the database at 39, while the 880M sits at 42, a narrow edge for the older part. The average benchmark score of the 880M is 8,040, which is actually 14.3% higher than the T600's 7,035, but this is driven by the 880M's limited benchmark set. The T600 has nine recorded benchmark scores spanning multiple DirectX versions, compute, and 2D tests, while the 880M has only two OpenCL/Metal entries.

For builders today, the T600 is the practical choice: it is a modern Turing architecture part with a much lower power draw and a full PCIe 3.0 x16 interface. The 880M is an end-of-life Kepler mobile module with no standalone display outputs, making it unsuitable for desktop use without a proprietary carrier. The verdict is simple: pick the T600 for any new build or upgrade path, and only consider the 880M if you are servicing a laptop that specifically requires an MXM module with that form factor.

Architecture Differences

The two GPUs come from entirely different architectural generations. The GTX 880M uses the GK104 chip, built on Kepler architecture, fabricated on TSMC's 28 nm process. It contains 3,540 million transistors on a 294 mm² die, giving a transistor density of 12.0 million per square millimeter. The T600 uses the TU117 chip, built on Turing architecture, fabricated on TSMC's 12 nm process. It packs 4,700 million transistors into a smaller 200 mm² die, yielding a much higher density of 23.5 million per square millimeter.

The compute layout differs significantly. The 880M features 1,536 shading units, 128 texture mapping units, and 32 ROPs. The T600 has only 640 shading units, 40 TMUs, and 32 ROPs. Despite having fewer than half the shading units, the T600 achieves a higher pixel rate of 42.72 GPixel/s versus the 880M's 31.78 GPixel/s, thanks to its higher boost clock. The texture rate tells the opposite story: the 880M reaches 127.1 GTexel/s, while the T600 manages only 53.40 GTexel/s, a consequence of the 880M's 128 TMUs.

The T600 has a substantial clock advantage. Its base clock is 735 MHz, but it boosts to 1,335 MHz, a 600 MHz uplift. The 880M runs at a 954 MHz base and 993 MHz boost, a much narrower boost range. The T600 also doubles the effective memory speed at 10 Gbps versus the 880M's 5 Gbps, although both end up with identical memory bandwidth of 160.0 GB/s because the 880M uses a 256-bit bus while the T600 uses a 128-bit bus.

Feature support also diverges. The T600 supports DirectX 12 (12_1) and Vulkan 1.4, while the 880M is limited to DirectX 12 (11_0) and Vulkan 1.2.175. Both support OpenGL 4.6. The T600 has native FP16 support rated at 3.418 TFLOPS with a 2:1 ratio, while the 880M has no recorded FP16 capability. The T600 also has a much lower power envelope at 40 W versus the 880M's 122 W.

Head-to-Head Benchmarks

The database contains only one direct comparison between these two cards: the Geekbench OpenCL test. The T600 wins decisively with a score of 27,875 against the 880M's 5,622. This is a 79.8% difference in favor of the T600, meaning the older Kepler card delivers less than a quarter of the OpenCL compute performance. This single result is the most important number in this comparison. It indicates that for any GPU compute task leveraging OpenCL, the T600 is in a completely different performance class.

The T600's other benchmark results reinforce this picture. In Geekbench Vulkan, it scores 25,580, which is close to its OpenCL result and confirms strong compute throughput across APIs. Its Passmark G3D score is 6,479, its G2D score is 756, and its GPU compute score is 2,402. The DirectX results are modest: 114 in DirectX 9, 49 in DirectX 11, 32 in DirectX 10, and 25 in DirectX 12. The 880M has no DirectX or Vulkan scores in the database, only Geekbench Metal at 10,458 and OpenCL at 5,622.

The average benchmark scores tell an interesting story. The 880M averages 8,040 across its two tests, while the T600 averages 7,035 across nine tests. The 880M's average is 14.3% higher, but this is misleading. The 880M's average is pulled up by its relatively strong Metal score of 10,458, which reflects Apple's Metal API rather than general compute. The T600's average is dragged down by very low DirectX 10 and 12 scores, which are not representative of its compute strength. The nearest rivals in the database confirm the positioning: the 880M sits between the Quadro P5000 at 8,039 and the GTX 650 Ti at 8,053, while the T600 sits near the GTX 680M at 7,023 and the GTX 970 at 7,157.

FAQ

Q: Which card has higher raw compute performance?

A: The T600. Its Geekbench OpenCL score of 27,875 crushes the 880M's 5,622, a 79.8% advantage. Its Vulkan score of 25,580 confirms this is not an API-specific fluke.

Q: Does the 880M have any advantage in memory capacity?

A: Yes. The 880M has 8 GB of GDDR5, double the T600's 4 GB of GDDR6. However, both cards have identical memory bandwidth at 160.0 GB/s.

Q: Which card is more power efficient?

A: The T600 by a wide margin. It has a 40 W TDP versus the 880M's 122 W, and it achieves this while delivering far higher compute scores.

Q: Can the 880M be used in a desktop PC?

A: The data indicates it is an MXM module with no display outputs of its own, marked as "Portable Device Dependent." It requires a portable device carrier. The T600 is a single-slot PCIe 3.0 x16 card with 4x mini-DisplayPort 1.4a outputs.

Q: Which card has better API support?

A: The T600. It supports DirectX 12 (12_1) and Vulkan 1.4, while the 880M is limited to DirectX 12 (11_0) and Vulkan 1.2.175. Both support OpenGL 4.6.

Q: Why does the 880M have a higher average benchmark score?

A: The 880M averages 8,040 versus the T600's 7,035, but this is due to the 880M's limited benchmark set. It has only two scores (Metal and OpenCL), while the T600 has nine scores including low DirectX numbers. The single direct comparison, OpenCL, heavily favors the T600.

Where Each One Wins

The T600 wins in nearly every measurable category. It dominates compute workloads, as shown by the 79.8% OpenCL advantage. It wins in pixel throughput with 42.72 GPixel/s versus 31.78 GPixel/s. It wins in API support, offering DirectX 12 (12_1), Vulkan 1.4, and FP16 compute. It wins decisively in power efficiency with a 40 W TDP versus 122 W. It wins in form factor flexibility as a standard single-slot PCIe card with four display outputs, making it suitable for workstation builds. Its 4 GB of GDDR6 memory, while smaller in capacity, runs at double the effective speed of the 880M's GDDR5.

The 880M wins in shading unit count with 1,536 versus 640, and in texture rate with 127.1 GTexel/s versus 53.40 GTexel/s. It also offers double the memory capacity at 8 GB, which could be relevant for workloads that need to hold very large datasets in VRAM. Its transistor count is lower at 3,540 million versus 4,700 million, but it uses a larger die at 294 mm², which is a historical curiosity rather than a practical advantage.

In practical terms, the T600 is the card for compute, modern API support, and low-power workstation builds. The 880M is only relevant if you specifically need an MXM module with 8 GB of VRAM for a compatible laptop. The benchmark data gives the T600 a clean sweep in the only direct comparison available.

Specification Differences

The two cards differ across nearly every specification category. The process node is 28 nm for the 880M and 12 nm for the T600. Transistor count is 3,540 million versus 4,700 million. Die size is 294 mm² versus 200 mm². Transistor density is 12.0M per mm² versus 23.5M per mm².

Clock speeds differ significantly. The 880M runs at 954 MHz base and 993 MHz boost. The T600 runs at 735 MHz base and 1,335 MHz boost. Memory speed is 5 Gbps effective for the 880M and 10 Gbps effective for the T600.

Memory configuration differs: 8 GB GDDR5 on a 256-bit bus for the 880M, 4 GB GDDR6 on a 128-bit bus for the T600. Both deliver 160.0 GB/s bandwidth. Shading units are 1,536 versus 640. TMUs are 128 versus 40. ROPs are 32 for both.

Pixel rates are 31.78 GPixel/s versus 42.72 GPixel/s. Texture rates are 127.1 GTexel/s versus 53.40 GTexel/s. FP32 compute is 3.050 TFLOPS for the 880M and 1.709 TFLOPS for the T600. The T600 additionally has FP16 at 3.418 TFLOPS with a 2:1 ratio.

Power figures differ sharply: 122 W TDP for the 880M, 40 W for the T600. The 880M uses an MXM Module slot width with an MXM-B (3.0) bus interface. The T600 is a single-slot card with PCIe 3.0 x16, and a suggested PSU of 200 W. Display outputs are "Portable Device Dependent" for the 880M, while the T600 offers 4x mini-DisplayPort 1.4a.

API support differs: DirectX 12 (11_0) versus 12 (12_1), Vulkan 1.2.175 versus 1.4, and both share OpenGL 4.6. Release dates are March 2014 for the 880M and April 2021 for the T600. Both are end-of-life. The 880M belongs to the GeForce 800M generation with GK104, while the T600 belongs to the Quadro Turing (Tx000) generation with TU117.