NVIDIA GeForce GTX 780 Ti vs NVIDIA P106-100 Comparison

The NVIDIA GeForce GTX 780 Ti and the NVIDIA P106-100 represent two very different approaches to GPU design from the same company, separated by nearly four years of architectural evolution. The GTX 780 Ti is a flagship Kepler part from 2013, while the P106-100 is a Pascal-based mining card from 2017 with no display outputs. Benchmark data shows the P106-100 winning both shared tests, but the comparison is far more nuanced than a simple win count suggests, as the two cards target entirely different workloads and system configurations.

Head-to-Head Benchmarks

The head-to-head data contains two shared benchmarks, and the P106-100 wins both. In Geekbench OpenCL, the P106-100 scores 35,951 against the GTX 780 Ti’s 27,326, a delta of -24% from the perspective of the older card. That is a substantial margin, placing the Pascal part roughly a quarter ahead in raw compute throughput as measured by this test. The gap narrows somewhat in Geekbench Vulkan, where the P106-100 scores 32,897 versus 27,238 for the GTX 780 Ti, a delta of -17.2%. Still, the P106-100 maintains a clear lead in both API environments.

Looking at the broader benchmark picture, the GTX 780 Ti’s average benchmark score across all recorded tests is 24,236, while the P106-100 averages 23,249. This is a curious inversion: the P106-100 wins the two head-to-head tests, yet its overall average is about 4% lower than the GTX 780 Ti’s average. The explanation lies in the test sets themselves. The GTX 780 Ti has three recorded benchmarks — Geekbench Metal (18,144), OpenCL (27,326), and Vulkan (27,238) — while the P106-100 has three different ones: 3DMark Steel Nomad DX12 (899), OpenCL (35,951), and Vulkan (32,897). The inclusion of the DX12 test, where the score is dramatically lower on an absolute scale, drags down the P106-100’s average despite its strong OpenCL and Vulkan showings.

The percentile rankings reinforce this mixed picture. The GTX 780 Ti sits at the 70th percentile among all GPUs, while the P106-100 sits at the 68th. Both are mid-pack performers, but the GTX 780 Ti edges ahead in overall standing. The nearest rivals for the GTX 780 Ti include the GeForce GTX 1630 (average 24,277, delta -0.2%), the RTX 2080 SUPER (24,170, +0.3%), and the AMD RX 6800S (24,063, +0.7%). The P106-100’s nearest rivals are the AMD Radeon Pro Vega 16 (23,250, delta 0%), the RX 6600M (23,273, -0.1%), and the R9 M290X (23,276, -0.1%). These rival clusters show that both cards sit in a tightly packed performance band, where a few percent separates them from much newer and more expensive hardware.

Architecture Differences

The architectural gap between these two cards is generational. The GTX 780 Ti uses the GK110B chip on the Kepler architecture, built on a 28 nm process at TSMC. The die is large and complex: 7,080 million transistors packed into 561 mm², yielding a transistor density of 12.6 million per square millimeter. The P106-100, by contrast, uses the GP106 chip on the Pascal architecture, also from TSMC but on a 16 nm process. It contains 4,400 million transistors on a 200 mm² die, achieving a density of 22.0 million per square millimeter. The newer process allows Pascal to pack nearly twice the transistor density into less than half the die area.

Clock speeds tell the efficiency story. The GTX 780 Ti runs at a base of 875 MHz and boosts to 928 MHz, while the P106-100 runs at 1,506 MHz base and 1,709 MHz boost. The Pascal card operates at nearly double the clock frequency, which explains how it can deliver competitive compute performance with far fewer cores. The GTX 780 Ti has 2,880 shading units, 240 texture mapping units, and 48 ROPs. The P106-100 has 1,280 shading units, 80 TMUs, and 48 ROPs. Despite having less than half the shading units and a third of the TMUs, the P106-100 nearly matches the GTX 780 Ti in FP32 throughput: 4.375 TFLOPS versus 5.345 TFLOPS. The GTX 780 Ti still holds the raw compute crown, but the efficiency gap is stark.

Memory configurations diverge significantly. The GTX 780 Ti uses 3 GB of GDDR5 on a 384-bit bus, delivering 336.6 GB/s of bandwidth. The P106-100 uses 6 GB of GDDR5 on a 192-bit bus, delivering 192.2 GB/s. The GTX 780 Ti has 75% more bandwidth, which is critical for high-resolution gaming, but the P106-100 has double the capacity, which is more useful for compute workloads that need large working sets. Pixel and texture rates follow the core and clock differences: the GTX 780 Ti achieves 55.68 GPixel/s and 222.7 GTexel/s, while the P106-100 achieves 82.03 GPixel/s and 136.7 GTexel/s. The Pascal card fills pixels faster but textures slower.

Feature support also differs. The GTX 780 Ti supports DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.175. The P106-100 supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The newer architecture carries a higher DirectX feature level and a newer Vulkan version. The P106-100 also lists FP16 performance of 68.36 GFLOPS at a 1:64 ratio, a capability the GTX 780 Ti does not list. The GTX 780 Ti is a dual-slot card with 1x 6-pin and 1x 8-pin power connectors and a 250 W TDP, while the P106-100 is also dual-slot but uses only a single 6-pin connector and has a 120 W TDP. The power draw difference is substantial: the P106-100 uses less than half the power of the GTX 780 Ti.

FAQ

Q: Which card has a higher average benchmark score?

A: The GTX 780 Ti has an average benchmark score of 24,236, while the P106-100 averages 23,249. The GTX 780 Ti also sits at the 70th percentile among all GPUs, two points above the P106-100’s 68th percentile.

Q: Why does the P106-100 win both head-to-head benchmarks if its average score is lower?

A: The P106-100 wins Geekbench OpenCL (35,951 vs 27,326) and Geekbench Vulkan (32,897 vs 27,238), but its average includes a 3DMark Steel Nomad DX12 score of 899, a test the GTX 780 Ti does not have. That low DX12 result pulls the average down despite strong OpenCL and Vulkan performance.

Q: How do the memory configurations differ?

A: The GTX 780 Ti has 3 GB of GDDR5 on a 384-bit bus with 336.6 GB/s bandwidth. The P106-100 has 6 GB of GDDR5 on a 192-bit bus with 192.2 GB/s bandwidth. The GTX 780 Ti offers higher bandwidth, while the P106-100 offers double the capacity.

Q: What are the power requirements for each card?

A: The GTX 780 Ti has a 250 W TDP, uses 1x 6-pin and 1x 8-pin power connectors, and requires a 600 W suggested PSU. The P106-100 has a 120 W TDP, uses a single 6-pin connector, and requires a 300 W suggested PSU.

Q: Can the P106-100 be used for display output?

A: No. The P106-100 has no display outputs, while the GTX 780 Ti offers 2x DVI, 1x HDMI 1.4a, and 1x DisplayPort 1.2. The P106-100 is designed solely for compute or mining workloads.

Q: Which card has a higher transistor density?

A: The P106-100 has a transistor density of 22.0 million per square millimeter on a 16 nm process, while the GTX 780 Ti has 12.6 million per square millimeter on a 28 nm process. The P106-100’s newer node allows for much denser packing.

Specification Differences

The two cards differ across nearly every major specification. The process node is 28 nm for the GTX 780 Ti versus 16 nm for the P106-100. The GTX 780 Ti packs 7,080 million transistors on a 561 mm² die, while the P106-100 has 4,400 million on 200 mm². Transistor density is 12.6M per mm² versus 22.0M per mm². Base clocks are 875 MHz versus 1,506 MHz, and boost clocks are 928 MHz versus 1,709 MHz. Memory speed is 1,753 MHz (7 Gbps effective) versus 2,002 MHz (8 Gbps effective).

The GTX 780 Ti has 2,880 shading units, 240 TMUs, and 48 ROPs. The P106-100 has 1,280 shading units, 80 TMUs, and 48 ROPs. Pixel rate is 55.68 GPixel/s versus 82.03 GPixel/s, and texture rate is 222.7 GTexel/s versus 136.7 GTexel/s. FP32 performance is 5.345 TFLOPS versus 4.375 TFLOPS. The GTX 780 Ti has no listed FP16 performance, while the P106-100 has 68.36 GFLOPS at a 1:64 ratio. TDP is 250 W versus 120 W. Power connectors are 1x 6-pin + 1x 8-pin versus 1x 6-pin. Suggested PSU is 600 W versus 300 W. Bus interface is PCIe 3.0 x16 versus PCIe 1.0 x16. Display outputs are 2x DVI, 1x HDMI 1.4a, 1x DisplayPort 1.2 versus no outputs. DirectX support is 12 (11_1) versus 12 (12_1). Vulkan support is 1.2.175 versus 1.4. Dimensions are 267 mm length, 111 mm height, 38 mm width versus 250 mm length only. Release dates are 2013-11-06 versus 2017-06-18. The GTX 780 Ti has a launch MSRP of 699 USD; the P106-100 has no listed launch MSRP.

The Verdict

The data presents a clear split based on use case. The GTX 780 Ti is the better overall GPU when judged by percentile rank and average score, and it is the only one of the two with display outputs, making it the obvious choice for any system that needs to drive a monitor. Its 336.6 GB/s bandwidth and 5.345 TFLOPS of FP32 performance give it advantages in bandwidth-bound and raw-compute scenarios. The P106-100, however, wins the two benchmarks shared with the GTX 780 Ti by margins of 24% and 17.2%, and it does so while drawing less than half the power (120 W versus 250 W) and requiring a 300 W PSU instead of 600 W. Its 6 GB memory capacity is double that of the GTX 780 Ti, which is valuable for workloads that need larger data sets in memory. The P106-100 also carries newer API support, including DirectX 12 (12_1) and Vulkan 1.4, compared to the GTX 780 Ti’s DirectX 12 (11_1) and Vulkan 1.2.175.

Where Each One Wins

The GTX 780 Ti wins in raw compute throughput, with 5.345 TFLOPS against the P106-100’s 4.375 TFLOPS. It also wins decisively in memory bandwidth at 336.6 GB/s versus 192.2 GB/s, and in texture fill rate at 222.7 GTexel/s versus 136.7 GTexel/s. It has a higher average benchmark score (24,236 vs 23,249) and a higher percentile rank (70th vs 68th). It is the only card with display outputs, making it the sole option for gaming or any visual output workload. Its nearest rivals include the RTX 2080 SUPER and RX 6800S, placing it in faster company than the P106-100’s rival set of Radeon Pro Vega 16 and RX 6600M.

The P106-100 wins in the two shared benchmark tests: Geekbench OpenCL by 24% and Geekbench Vulkan by 17.2%. It has a higher pixel rate (82.03 GPixel/s vs 55.68 GPixel/s), double the memory capacity (6 GB vs 3 GB), and a significantly higher transistor density (22.0M per mm² vs 12.6M per mm²). It draws 120 W versus 250 W, requires a 300 W PSU versus 600 W, and uses a single 6-pin connector versus a 6-pin plus 8-pin setup. It supports newer API versions and has no display outputs, indicating a design intent for compute or mining environments where power efficiency and memory capacity matter more than connectivity. For a headless compute node or a mining rig, the P106-100 is the data-backed choice; for any system requiring display output or high memory bandwidth, the GTX 780 Ti holds the advantage.