AMD Instinct MI455X vs NVIDIA GeForce RTX 5060 Mobile Comparison

Head-to-Head Benchmarks

The database contains no direct benchmark comparisons between the AMD Instinct MI455X and the NVIDIA GeForce RTX 5060 Mobile. The head-to-head benchmark table is empty, and neither part has recorded benchmark scores for the MI455X. The MI455X shows zero benchmark entries and an average score of zero, while the RTX 5060 Mobile has a full suite of ten recorded tests.

The RTX 5060 Mobile delivers measurable results across multiple APIs. Its highest raw score appears in Geekbench OpenCL at 96,969 points, with Geekbench Vulkan close behind at 96,451 points. In 3DMark Steel Nomad DX12, it records 3,013.5 points. PassMark results show a G3D score of 18,852, a G2D score of 876, and a GPU compute score of 7,607. Legacy DirectX tests show 203 in DirectX 9, 168 in DirectX 11, 119 in DirectX 10, and 87 in DirectX 12.

The MI455X has no comparable measurements in the database. Its percentile ranking sits at 50, while the RTX 5060 Mobile ranks at 67. The RTX 5060 Mobile also carries an average benchmark score of 22,435, derived from its ten tests. Without any recorded scores for the MI455X, no direct performance deltas can be computed. The wins count stands at zero for each part.

The Verdict

Based strictly on recorded data, the NVIDIA GeForce RTX 5060 Mobile is the only part with measurable benchmark performance. The AMD Instinct MI455X has no benchmark scores, no average score, and no rival comparisons in the database. Any selection between these two must rely on architectural specifications rather than performance measurements.

The RTX 5060 Mobile sits in the 67th percentile among all GPUs in the database. Its nearest rivals confirm competitive positioning: the AMD Radeon RX 7700 XT averages 22,549 points, placing the RTX 5060 Mobile 0.5% behind that part. The RTX 5060 Mobile leads the AMD Radeon RX 5700 by 1.2% (22,170 points), leads the AMD Radeon RX 6700S by 1.3% (22,154 points), and trails the NVIDIA GeForce RTX 4060 Mobile by 1.3% (22,729 points). These deltas indicate a tightly grouped performance cluster.

The MI455X presents an entirely different profile. It is a 2 nm TSMC part with 320,000 million transistors on a 2,990 mm² die, using HBM4 memory totaling 432 GB across a 24,576-bit bus. Its TDP is 2,300 W with a suggested power supply of 2,700 W. The RTX 5060 Mobile uses 45 W on a 5 nm TSMC process with 21,900 million transistors on a 181 mm² die, paired with 8 GB of GDDR7 on a 128-bit bus.

For users requiring recorded performance data, the RTX 5060 Mobile is the only option with evidence. For users whose requirements align with the MI455X specifications, the data simply does not yet include benchmark results.

Architecture Differences

The two parts diverge fundamentally in architecture. The MI455X uses CDNA 5.0, AMD's compute-focused design, while the RTX 5060 Mobile uses Blackwell 2.0, NVIDIA's Blackwell generation for mobile.

Manufacturing processes differ significantly. The MI455X is built on a 2 nm process at TSMC with 320,000 million transistors on a 2,990 mm² die, yielding a transistor density of 107.0 million per mm². The RTX 5060 Mobile uses a 5 nm TSMC process with 21,900 million transistors on a 181 mm² die, achieving 121.0 million transistors per mm². Despite the larger node, the RTX 5060 Mobile achieves higher transistor density per square millimeter.

Compute resources are vastly different. The MI455X contains 32,768 shading units and 1,024 texture mapping units, with no ROPs reported and a pixel rate of 0 MPixel/s. The RTX 5060 Mobile has 3,328 shading units, 104 TMUs, and 48 ROPs, with a pixel rate of 69.84 GPixel/s. The MI455X reports a texture rate of 2,457.6 GTexel/s versus 151.3 GTexel/s for the RTX 5060 Mobile. Floating-point throughput shows 157.3 TFLOPS for the MI455X in both FP32 and FP16 (1:1 ratio), while the RTX 5060 Mobile delivers 9.684 TFLOPS in both.

Memory systems are entirely different classes. The MI455X uses HBM4 with 432 GB capacity, a 24,576-bit bus, and 23.3 TB/s bandwidth. The RTX 5060 Mobile uses GDDR7 with 8 GB, a 128-bit bus, and 384.0 GB/s bandwidth. Clock speeds: the MI455X runs at 1000 MHz base and 2400 MHz boost with memory at 1900 MHz (7.6 Gbps effective). The RTX 5060 Mobile runs at 952 MHz base and 1455 MHz boost with memory at 1500 MHz (24 Gbps effective).

Ray tracing and tensor cores exist only on the RTX 5060 Mobile: 26 ray tracing cores and 104 tensor cores. The MI455X reports none for either. API support also differs. The RTX 5060 Mobile supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The MI455X reports N/A for DirectX, OpenGL, and Vulkan.

FAQ

Q: Which GPU has higher floating-point performance?

A: The AMD Instinct MI455X, with 157.3 TFLOPS in both FP32 and FP16, versus 9.684 TFLOPS for the NVIDIA GeForce RTX 5060 Mobile in both precisions.

Q: How do their memory capacities compare?

A: The MI455X has 432 GB of HBM4 with a 24,576-bit bus and 23.3 TB/s bandwidth. The RTX 5060 Mobile has 8 GB of GDDR7 with a 128-bit bus and 384.0 GB/s bandwidth.

Q: Which part has ray tracing support?

A: The RTX 5060 Mobile includes 26 ray tracing cores. The MI455X reports no ray tracing cores.

Q: What are their power requirements?

A: The MI455X has a TDP of 2,300 W with a suggested power supply of 2,700 W. The RTX 5060 Mobile has a TDP of 45 W with no suggested power supply listed.

Q: What API levels does each support?

A: The RTX 5060 Mobile supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The MI455X reports N/A for all three APIs.

Q: Which GPU has recorded benchmark scores?

A: Only the RTX 5060 Mobile has benchmark data, with ten tests spanning 3DMark, Geekbench, and PassMark suites. The MI455X has no recorded benchmarks.

Where Each One Wins

The RTX 5060 Mobile wins in every measurable benchmark category because it is the only part with recorded data. Its average benchmark score of 22,435 places it in the 67th percentile among all GPUs. The nearest rival comparisons show it within 1.3% of the RTX 4060 Mobile and RX 7700 XT, while leading the RX 5700 and RX 6700S by 1.2% and 1.3% respectively. The recorded scores span compute workloads (Geekbench OpenCL at 96,969), graphics APIs (Geekbench Vulkan at 96,451), and modern rasterization (3DMark Steel Nomad at 3,013.5). PassMark results show strong DirectX 9 performance (203) and weaker DirectX 12 results (87), suggesting the driver stack favors legacy APIs in that specific test.

The MI455X wins in raw specification comparisons across compute resources, memory capacity, bandwidth, and process node. It offers 32,768 shading units versus 3,328 for the RTX 5060 Mobile, 1,024 TMUs versus 104, and 2,457.6 GTexel/s versus 151.3. Its 432 GB HBM4 pool with 23.3 TB/s bandwidth dwarfs the 8 GB GDDR7 with 384.0 GB/s. The 2 nm process node represents a generational leap over the 5 nm node, despite lower transistor density (107.0M per mm² versus 121.0M per mm²). The MI455X also has a 2,300 W TDP, reflecting a data-center-class design, while the RTX 5060 Mobile operates at 45 W for portable devices.

The MI455X uses PCIe 6.0 x16, while the RTX 5060 Mobile uses PCIe 5.0 x16. The MI455X has no display outputs, while the RTX 5060 Mobile's outputs are portable-device dependent. The MI455X is an EAM Module with no power connectors, while the RTX 5060 Mobile is an IGP with no power connectors. Neither part lists a launch MSRP.

Specification Differences

The recorded specifications that differ between the two parts are extensive. Process node: 2 nm for the MI455X versus 5 nm for the RTX 5060 Mobile, both at TSMC. Transistors: 320,000 million versus 21,900 million. Die size: 2,990 mm² versus 181 mm². Transistor density: 107.0M per mm² versus 121.0M per mm².

Clocks: base 1000 MHz versus 952 MHz, boost 2400 MHz versus 1455 MHz, memory 1900 MHz (7.6 Gbps effective) versus 1500 MHz (24 Gbps effective). Memory: 432 GB HBM4 versus 8 GB GDDR7, bus width 24,576 bit versus 128 bit, bandwidth 23.3 TB/s versus 384.0 GB/s.

Compute units: 32,768 shading units versus 3,328, 1,024 TMUs versus 104, 0 ROPs versus 48, no ray tracing cores versus 26, no tensor cores versus 104. Pixel rate: 0 MPixel/s versus 69.84 GPixel/s. Texture rate: 2,457.6 GTexel/s versus 151.3 GTexel/s. FP32: 157.3 TFLOPS versus 9.684 TFLOPS. FP16: 157.3 TFLOPS versus 9.684 TFLOPS, both at 1:1 ratio.

Power: TDP 2,300 W versus 45 W, suggested PSU 2,700 W versus none. Form factor: EAM Module versus IGP. Bus interface: PCIe 6.0 x16 versus PCIe 5.0 x16. Display outputs: none versus portable-device dependent. APIs: DirectX N/A versus 12 Ultimate (12_2), OpenGL N/A versus 4.6, Vulkan N/A versus 1.4.

Release dates: the MI455X released on July 22, 2026, while the RTX 5060 Mobile released on May 19, 2025. The MI455X has no production status listed, while the RTX 5060 Mobile is active. The MI455X lists Radeon Instinct as its predecessor, and the RTX 5060 Mobile lists GeForce 40 Mobile. Neither part has a successor listed.