AMD Radeon 760M vs NVIDIA Rubin GPU Comparison

Head-to-Head Benchmarks

The recorded data shows no direct head-to-head benchmark results between the AMD Radeon 760M and the NVIDIA Rubin GPU. The head-to-head comparison table is empty, and neither product records a win in direct comparison tests. This absence of comparable benchmark scores is significant: the AMD Radeon 760M has ten recorded benchmark entries across multiple test suites, while the NVIDIA Rubin GPU has zero recorded benchmark scores in the database.

The AMD Radeon 760M's benchmark results are substantial for an integrated graphics processor. Its strongest recorded score is 30,336 in Geekbench Vulkan, followed by 20,255 in Geekbench OpenCL. In Passmark testing, the 760M scores 5,310 in G3D, 890 in G2D, and 2,840 in GPU Compute. DirectX performance shows 65 in DirectX 9, 52 in DirectX 11, 25 in DirectX 12, and 19 in DirectX 10. The 3DMark Steel Nomad DX12 test records a score of 400. These results place the 760M at the 35th percentile among all GPUs tracked in the database.

The average benchmark score for the AMD Radeon 760M is 6,019. Its nearest rivals in the database show remarkably close aggregate performance: the AMD Radeon RX 6400 averages 6,001, a delta of 0.3% ahead of the 760M; the NVIDIA GeForce GTX 770M averages 6,000, also 0.3% ahead; the NVIDIA RTX PRO 6000 Blackwell Server averages 5,996, 0.4% ahead; and the NVIDIA Quadro P2000 averages 6,049, 0.5% behind the 760M. The benchmark data indicates the 760M sits in a tight performance cluster, with all four nearest rivals within half a percentage point of its average score.

The NVIDIA Rubin GPU has no benchmark scores recorded. Its percentile ranking is listed at 50, but this value is not supported by any test results, and its average benchmark score is 0. The database cannot compute comparative performance deltas for this product because it lacks the necessary measurement data. Consequently, the head-to-head comparison relies entirely on architectural specifications and the one-sided benchmark results of the AMD part.

Architecture Differences

The architectural contrast between these two products is extensive. The AMD Radeon 760M uses the Phoenix chip built on RDNA 3.0 architecture, part of the Navi III IGP generation. It is manufactured on a 4 nm process at TSMC, containing 25,390 million transistors on a 178 mm² die, yielding a transistor density of 142.6 million transistors per square millimeter. The NVIDIA Rubin GPU uses the GR100 chip built on the Rubin architecture, part of the Server Rubin generation. It is manufactured on a 3 nm process at TSMC, containing 336,000 million transistors on a 1,456 mm² die, yielding a transistor density of 230.8 million transistors per square millimeter.

The Rubin GPU has over 13 times the transistor count of the Radeon 760M and a die that is more than eight times larger. Its transistor density is substantially higher as well. The 760M operates with a base clock of 800 MHz and a boost clock of 2,599 MHz. The Rubin GPU has a lower base clock of 700 MHz and a lower boost clock of 2,267 MHz, but this is offset by its far greater execution resource count.

The AMD Radeon 760M contains 512 shading units, 32 texture mapping units, 16 render output units, and 8 ray tracing cores. It has no tensor cores. The NVIDIA Rubin GPU contains 28,672 shading units, 896 texture mapping units, 24 render output units, and 896 tensor cores. The Rubin GPU does not list ray tracing cores in its specifications. The Rubin GPU has 56 times the shading units of the 760M, 28 times the texture mapping units, and 1.5 times the render output units.

Memory configurations diverge completely. The AMD Radeon 760M uses system shared memory, with the memory type, bus width, and bandwidth all dependent on the host system. The NVIDIA Rubin GPU has 288 GB of dedicated HBM4 memory on a 16,384-bit bus, delivering 22.1 TB/s of bandwidth. Its memory clock is listed at 2,695 MHz with 10.8 Gbps effective data rate. The 760M has no dedicated memory of its own.

Compute throughput numbers reflect the massive scale difference. The AMD Radeon 760M delivers 5.323 TFLOPS of FP32 performance and the same 5.323 TFLOPS of FP16 performance in a 1:1 ratio. The NVIDIA Rubin GPU delivers 130.0 TFLOPS of FP32 performance and 260.0 TFLOPS of FP16 performance in a 2:1 ratio. The Rubin GPU has approximately 24.4 times the FP32 throughput and 48.8 times the FP16 throughput of the 760M. Pixel and texture rates tell a similar story: the 760M produces 41.58 GPixel/s and 83.17 GTexel/s, while the Rubin GPU produces 54.41 GPixel/s and 2,031.2 GTexel/s. The Rubin GPU has roughly 1.3 times the pixel rate and 24.4 times the texture rate.

Power requirements are equally divergent. The AMD Radeon 760M has a TDP of 15 W, uses no power connectors, and is an integrated graphics processor with motherboard-dependent display outputs. The NVIDIA Rubin GPU has a TDP of 2,300 W, is an SXM module, has no display outputs, and requires a suggested power supply of 2,700 W. The bus interfaces differ as well: the 760M uses PCIe 4.0 x8, while the Rubin GPU uses PCIe 6.0 x16.

API support is asymmetric. The AMD Radeon 760M supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The NVIDIA Rubin GPU lists N/A for DirectX, OpenGL, and Vulkan, reflecting its server-oriented positioning rather than a consumer graphics role. The 760M was released on 2024-01-30 and its predecessor is the Navi II IGP. The Rubin GPU was released on 2025-12-31 and its predecessor is Server Blackwell. The 760M is an integrated part with a 15 W power envelope, while the Rubin GPU is a massive server accelerator with a 2,300 W power envelope.

FAQ

Q: Does the NVIDIA Rubin GPU outperform the AMD Radeon 760M in benchmarks?

A: The database contains no benchmark scores for the NVIDIA Rubin GPU. Its average benchmark score is recorded as 0, and it has no nearest rivals listed. The AMD Radeon 760M has ten recorded benchmark scores with an average of 6,019, but no direct comparison data exists between the two products.

Q: How does the AMD Radeon 760M compare to its nearest rivals in the database?

A: The AMD Radeon 760M averages 6,019 in benchmark scores. The AMD Radeon RX 6400 averages 6,001 (0.3% ahead), the NVIDIA GeForce GTX 770M averages 6,000 (0.3% ahead), the NVIDIA RTX PRO 6000 Blackwell Server averages 5,996 (0.4% ahead), and the NVIDIA Quadro P2000 averages 6,049 (0.5% behind). All four rivals sit within 0.5 percentage points of the 760M's average score.

Q: What is the transistor count difference between the two GPUs?

A: The AMD Radeon 760M contains 25,390 million transistors on a 178 mm² die. The NVIDIA Rubin GPU contains 336,000 million transistors on a 1,456 mm² die. The Rubin GPU has more than 13 times the transistor count and a die over eight times larger.

Q: What memory configuration does each GPU use?

A: The AMD Radeon 760M uses system shared memory with bandwidth dependent on the host system. The NVIDIA Rubin GPU has 288 GB of HBM4 memory on a 16,384-bit bus with 22.1 TB/s bandwidth and a 2,695 MHz memory clock.

Q: What is the power requirement difference between the two products?

A: The AMD Radeon 760M has a 15 W TDP and uses no power connectors. The NVIDIA Rubin GPU has a 2,300 W TDP and requires a suggested power supply of 2,700 W. The 760M is an integrated part, while the Rubin GPU is an SXM module.

Q: What API support does each GPU provide?

A: The AMD Radeon 760M supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The NVIDIA Rubin GPU lists N/A for DirectX, OpenGL, and Vulkan, indicating its server-oriented design with no consumer graphics API support.

The Verdict

The data indicates two products designed for entirely different purposes. The AMD Radeon 760M is an integrated graphics processor with a 15 W TDP, system shared memory, and full consumer API support including DirectX 12 Ultimate and Vulkan 1.4. Its benchmark results place it at the 35th percentile among all GPUs, with an average score of 6,019 and nearest rivals within 0.5% of its performance level. It is suitable for systems requiring integrated graphics with modest power draw.

The NVIDIA Rubin GPU is a server accelerator with a 2,300 W TDP, 288 GB of HBM4 memory, 896 tensor cores, and no display outputs. It has no recorded benchmark scores and no API support for consumer graphics. Its specifications indicate a compute-focused product for server environments, with 130.0 TFLOPS of FP32 performance and 260.0 TFLOPS of FP16 performance. Its 50th percentile ranking is recorded without supporting benchmark data.

The choice between these products depends entirely on the use case. The AMD Radeon 760M serves systems needing integrated graphics with consumer API support and low power consumption. The NVIDIA Rubin GPU serves server deployments requiring massive compute throughput, HBM4 memory, and tensor core acceleration. They do not compete in the same market segment, and the database contains no direct comparison results to suggest otherwise.

Specification Differences

The following specifications differ between the two products:

• Chip: Phoenix (AMD) versus GR100 (NVIDIA)
• Architecture: RDNA 3.0 versus Rubin
• Generation: Navi III IGP (Phoenix) versus Server Rubin (Rxx)
• Process node: 4 nm versus 3 nm
• Transistors: 25,390 million versus 336,000 million
• Die size: 178 mm² versus 1,456 mm²
• Transistor density: 142.6M / mm² versus 230.8M / mm²
• Base clock: 800 MHz versus 700 MHz
• Boost clock: 2,599 MHz versus 2,267 MHz
• Memory size: System Shared versus 288 GB
• Memory type: System Shared versus HBM4
• Memory bus width: System Shared versus 16,384 bit
• Memory bandwidth: System Dependent versus 22.1 TB/s
• Memory clock: System Shared versus 2,695 MHz 10.8 Gbps effective
• Shading units: 512 versus 28,672
• Texture mapping units: 32 versus 896
• Render output units: 16 versus 24
• Ray tracing cores: 8 versus not listed
• Tensor cores: not listed versus 896
• Pixel rate: 41.58 GPixel/s versus 54.41 GPixel/s
• Texture rate: 83.17 GTexel/s versus 2,031.2 GTexel/s
• FP32 performance: 5.323 TFLOPS versus 130.0 TFLOPS
• FP16 performance: 5.323 TFLOPS (1:1) versus 260.0 TFLOPS (2:1)
• TDP: 15 W versus 2,300 W
• Slot width: IGP versus SXM Module
• Power connectors: None versus not listed
• Suggested PSU: not listed versus 2,700 W
• Bus interface: PCIe 4.0 x8 versus PCIe 6.0 x16
• Display outputs: Motherboard Dependent versus No outputs
• DirectX support: 12 Ultimate (12_2) versus N/A
• OpenGL support: 4.6 versus N/A
• Vulkan support: 1.4 versus N/A
• Release date: 2024-01-30 versus 2025-12-31
• Predecessor: Navi II IGP versus Server Blackwell

Where Each One Wins

The AMD Radeon 760M wins in scenarios requiring integrated graphics with consumer API compatibility. It supports DirectX 12 Ultimate, OpenGL 4.6, and Vulkan 1.4, making it applicable to systems running graphics workloads using these APIs. Its 15 W TDP and lack of power connectors suit low-power systems. Its benchmark scores, while modest, are recorded across multiple test suites, providing measurable performance data. Its nearest rivals all cluster within 0.5% of its average score, indicating consistent performance in its segment.

The NVIDIA Rubin GPU wins in compute-intensive server workloads. Its 130.0 TFLOPS FP32 and 260.0 TFLOPS FP16 performance dwarf the 760M's 5.323 TFLOPS in both precision formats. Its 896 tensor cores provide dedicated matrix computation resources absent from the 760M. Its 288 GB of HBM4 memory with 22.1 TB/s bandwidth and 16,384-bit bus enable data-intensive applications. Its 896 texture mapping units and 2,031.2 GTexel/s texture rate indicate substantial throughput capacity. Its PCIe 6.0 x16 interface provides high-bandwidth host connectivity.

The AMD Radeon 760M also wins in physical footprint and integration flexibility. It is an IGP with no slot width, no power connectors, and motherboard-dependent display outputs. The NVIDIA Rubin GPU is an SXM module with no display outputs and a 2,300 W TDP. The 760M's 4 nm process and 178 mm² die represent a compact implementation, while the Rubin GPU's 3 nm process and 1,456 mm² die represent a massive server-class package.

The NVIDIA Rubin GPU wins in memory capability. Its 288 GB of HBM4 memory with 22.1 TB/s bandwidth is entirely self-contained, whereas the 760M depends on system memory with system-dependent bandwidth. The Rubin GPU's memory clock of 2,695 MHz with 10.8 Gbps effective data rate provides high-speed access to its dedicated memory pool.

The AMD Radeon 760M wins in consumer graphics API support. The Rubin GPU lists N/A for DirectX, OpenGL, and Vulkan, meaning it cannot run consumer graphics workloads through these APIs. The 760M's support for DirectX 12 Ultimate, OpenGL 4.6, and Vulkan 1.4 makes it applicable to a wide range of consumer and professional graphics applications.

The NVIDIA Rubin GPU wins in raw compute scale. Its shading unit count is 56 times higher, its FP32 throughput is approximately 24.4 times higher, and its FP16 throughput is approximately 48.8 times higher than the 760M. Its transistor count exceeds the 760M by a factor of over 13. Its texture rate exceeds the 760M by a factor of approximately 24.4.

The AMD Radeon 760M wins in power efficiency per the recorded data. Its 15 W TDP versus the Rubin GPU's 2,300 W TDP represents a 153-fold difference in power draw. Its pixel rate of 41.58 GPixel/s is comparable to the Rubin GPU's 54.41 GPixel/s despite the enormous power and resource differences, indicating the 760M delivers a substantial fraction of pixel throughput per watt.

The NVIDIA Rubin GPU wins in memory bandwidth and capacity. Its 22.1 TB/s bandwidth versus the 760M's system-dependent bandwidth, and its 288 GB capacity versus system shared memory, provide clear advantages for memory-bound workloads. Its 16,384-bit bus width enables the high bandwidth figure, while the 760M's bus width is system dependent.

The AMD Radeon 760M wins in release timing for consumer availability, with a release date of 2024-01-30 versus the Rubin GPU's 2025-12-31. The 760M's predecessor is Navi II IGP, while the Rubin GPU's predecessor is Server Blackwell. The 760M has recorded benchmark data across ten tests, while the Rubin GPU has none, meaning only the 760M has measurable performance evidence in the database.