NVIDIA GeForce GTX 760 Ti OEM

The NVIDIA GeForce GTX 760 Ti OEM is a Kepler-architecture graphics card from the GeForce 700 generation, built by TSMC on a 28 nm process. It carries 3,540 million transistors on a 294 mm² die, and the database places it at the 50th percentile of all GPUs — a squarely median performer. With no benchmark entries recorded and no nearest rivals listed, the available data consists of the card's hardware specifications and its percentile standing.

Benchmark Performance

The database lists no discrete benchmark scores for the GTX 760 Ti OEM — the benchmarks array is empty and the average benchmark score is 0. The only comparative metric available is the percentileVsAllGpus field, which places the card at the 50th percentile. That figure means the card sits exactly at the midpoint of the entire GPU performance distribution in the database: half of all GPUs rank above it, half rank below. This is a meaningful anchor for interpreting its specifications.

The raw compute numbers align with a median position. The 1,344 shading units run at a base clock of 915 MHz and a boost clock of 980 MHz, producing 2.634 TFLOPS of FP32 throughput. That is a modest figure by modern standards but was competitive for a mid-range card in its release era. The 112 texture mapping units generate a texture rate of 109.8 GTexel/s, and the 32 ROPs deliver a pixel rate of 27.44 GPixel/s. These rates suggest a card that can handle gaming at moderate resolutions with medium to high settings in titles from its time, but will struggle with modern workloads.

Because the nearestRivals field is empty, no exact percentage deltas can be reported against specific competitors. The 50th percentile is the sole comparative data point. It indicates that the GTX 760 Ti OEM was neither a performance outlier nor a compromise — it occupied the exact middle of the GPU market. This is typical of OEM-specific cards, which are often tuned to a conservative specification that balances capability for system integrators.

How It Compares

The database does not list any nearest rivals for the GTX 760 Ti OEM, so a direct competitor-by-competitor comparison with percentage deltas is not possible. Instead, the card's position can be understood through its generation context and its percentile ranking.

Within the GeForce 700 generation, the GTX 760 Ti OEM is an OEM-specific variant, distinguished by its GK104 chip and Kepler architecture. Its predecessor generation is GeForce 600, and its successor is GeForce 900. The 28 nm process node places it in the same manufacturing era as many mid-range cards of the early 2010s. The transistor density of 12.0M per square millimeter, derived from 3,540 million transistors on a 294 mm² die, reflects the design rules of that process node.

The 50th percentile ranking is the clearest comparative statement the database makes about this card. It tells us that, across the full spectrum of GPUs in the database, the GTX 760 Ti OEM performs at the median. That is a different position than a card that sits below or above the median. The card is, by definition, average.

The card's release date of September 26, 2013, and its end-of-life production status further contextualize its position. It was designed for a specific market window in the mid-2010s, and its OEM designation means it was primarily intended for pre-built systems rather than retail enthusiasts. The database does not record a launch MSRP for this card, consistent with its OEM-focused distribution model.

Ray Tracing and Feature Set

The GTX 760 Ti OEM has no ray tracing cores and no tensor cores — both fields are null in the FACT PACK. This is a direct consequence of its Kepler architecture, which predates the introduction of dedicated ray tracing hardware by several years. The card cannot accelerate ray-traced effects in hardware; any such workload would fall to the standard shading units, which lack the specialized processing paths needed for efficient ray traversal. In practice, this means the card is not suitable for ray-traced gaming or ray-traced rendering workloads.

The tensor core field is also null, meaning there is no hardware acceleration for AI-based features such as deep learning super sampling or neural network inference. Features that rely on tensor cores in modern GPUs are simply unavailable on this card.

The API support provides a more nuanced picture. The card supports DirectX 12 at the 11_0 feature level. This means it can run DirectX 12 applications, but only with the feature set defined by the 11_0 specification. Modern games that require higher DirectX 12 feature levels — such as mesh shaders, variable rate shading, or DirectX Raytracing — will not be able to use those features on this card. OpenGL 4.6 is fully supported, which covers a wide range of professional and open-source applications. Vulkan 1.2.175 is also supported, giving access to modern low-overhead rendering APIs.

The display output configuration includes 2 DVI ports, 1 HDMI 1.4a port, and 1 DisplayPort 1.2 port. The HDMI 1.4a standard caps output at a lower refresh rate for high resolutions, while DisplayPort 1.2 offers more headroom. For high-resolution displays, the DisplayPort connection is the recommended choice. The card connects to the system via PCIe 3.0 x16, which provides sufficient bandwidth for its memory subsystem and rendering pipeline.

Who Should Consider It

The GTX 760 Ti OEM is a gaming card at heart. Its 2.634 TFLOPS of FP32 compute, 27.44 GPixel/s pixel rate, and 109.8 GTexel/s texture rate are sufficient for gaming at medium settings in titles from its release era. The 50th percentile ranking confirms that it is a median performer — capable but not exceptional.

At standard gaming resolutions, the 2 GB GDDR5 memory on a 256-bit bus provides 192.3 GB/s of bandwidth, which is adequate for the texture loads and frame buffers of games from the early 2010s. Esports titles, older games, and indie games will run comfortably. Users who play these types of games and are looking for a functional GPU could find this card acceptable, provided they manage their settings expectations.

At higher resolutions, the card's limitations become apparent. The 2 GB frame buffer is a hard constraint — modern games with high-resolution textures can exceed 2 GB of memory usage even at standard resolutions. The 32 ROPs and 27.44 GPixel/s pixel rate also limit the card's ability to fill high-resolution frames. The memory bandwidth of 192.3 GB/s, while respectable for a 256-bit bus, is not enough to sustain high-resolution gaming with modern texture compression and rendering techniques.

The card's end-of-life production status means it is no longer manufactured. It is not a card that a new PC builder should seek out for a modern system. The suggested power supply of 450 W and the 170 W TDP are modest, but the card's age and lack of modern feature support make it a poor fit for contemporary gaming workloads.

FAQ

Q: Does the GTX 760 Ti OEM support hardware ray tracing?

A: No. The database lists no ray tracing cores for this card, and its Kepler architecture from 2013 predates hardware ray tracing.

Q: What graphics APIs does the card support?

A: It supports DirectX 12 at the 11_0 feature level, OpenGL 4.6, and Vulkan 1.2.175.

Q: How much VRAM does the card have, and what is its bandwidth?

A: It has 2 GB of GDDR5 memory on a 256-bit bus, with 192.3 GB/s of bandwidth and a 6 Gbps effective memory data rate.

Q: What power requirements does the card have?

A: The card has a TDP of 170 W, requires 2x 6-pin power connectors, and has a suggested power supply of 450 W.

Q: What display outputs are available on the card?

A: It has 2 DVI ports, 1 HDMI 1.4a port, and 1 DisplayPort 1.2 port.

Q: When was the card released, and what is its production status?

A: It was released on September 26, 2013, and its production status is end-of-life.

Memory Subsystem

The GTX 760 Ti OEM's memory subsystem consists of 2 GB of GDDR5 memory on a 256-bit bus. The memory clock is 1502 MHz, which yields a 6 Gbps effective data rate. The total bandwidth is 192.3 GB/s. This configuration was a standard mid-range setup in the Kepler era, balancing capacity, bus width, and clock speed.

The 256-bit bus width is the subsystem's strongest attribute. A wider bus allows more data to be transferred per memory clock cycle, which directly benefits bandwidth-sensitive workloads like high-resolution texturing and anti-aliasing. The 192.3 GB/s bandwidth is sufficient for gaming at medium settings and for older titles with high settings. It also supports the card's 109.8 GTexel/s texture rate without creating a significant bottleneck in most scenarios.

The 2 GB capacity is the subsystem's limiting factor. Modern games frequently exceed 2 GB of memory usage at standard resolutions with high-quality textures, and at higher resolutions, the demand is even greater. When the frame buffer fills, the card must spill over to system memory over the PCIe 3.0 x16 bus, which causes stuttering and frame time spikes. This is a fundamental constraint that cannot be overcome with driver updates or settings tweaks.

The pixel rate of 27.44 GPixel/s and the texture rate of 109.8 GTexel/s are well matched to the memory bandwidth. The card can fill pixels and sample textures at rates that the memory subsystem can feed. This balance is typical of a well-designed mid-range card — it is not held back by a single weak component, but it also does not have headroom in any one area. For gaming at medium settings, this is a workable configuration; for anything more demanding, the memory subsystem will be the first place the card shows its age.