AMD Radeon 860M vs AMD Ryzen Z2 Extreme GPU Comparison

Head-to-Head Benchmarks

The recorded data for these two parts does not include shared benchmark tests, so a direct head-to-head comparison on identical workloads is not possible from the database. The AMD Radeon 860M has results in Geekbench OpenCL and Vulkan, while the AMD Ryzen Z2 Extreme GPU has only a 3DMark Steel Nomad DX12 score. Because the tests differ, the average benchmark scores are not directly comparable in a meaningful way.

The Radeon 860M posts an average benchmark score of 26401, placing it at the 72nd percentile among all GPUs in the database. Its Geekbench OpenCL result is 22759, and its Vulkan result is 30043. The Ryzen Z2 Extreme GPU, by contrast, records an average benchmark score of 516, which places it at the 1st percentile. Its sole 3DMark Steel Nomad DX12 score is 516.

Interpreting these percentile positions is instructive. The 72nd percentile for the Radeon 860M indicates that it outperforms the majority of recorded GPUs. Its nearest rivals in the database are the NVIDIA GeForce MX550, with an average score of 26421 and a delta of -0.1%, the NVIDIA GeForce RTX 5060 at 26331 (delta 0.3%), the AMD Radeon RX 5700 XT 50th Anniversary at 26553 (delta -0.6%), and the NVIDIA RTX A4000 at 26683 (delta -1.1%). These deltas show that the Radeon 860M is effectively within a narrow band of performance around these discrete and professional cards, sitting just 0.1% below the MX550 and 0.3% above the RTX 5060 in average score. The spread from -1.1% to 0.3% across the four rivals indicates that the Radeon 860M occupies a competitive position in this performance tier.

The Ryzen Z2 Extreme GPU, with its 1st percentile ranking, sits at the very bottom of the database distribution. Its nearest rivals are all legacy or low-end parts: Intel HD Graphics P4000 at 534 (delta -3.4%), AMD Radeon HD 6870 at 536 (delta -3.7%), AMD Radeon HD 6750M at 484 (delta 6.6%), and AMD Radeon HD 6770M at 569 (delta -9.3%). The deltas show the Z2 Extreme GPU is 3.4% below the HD P4000 and 3.7% below the HD 6870, while it sits 6.6% above the HD 6750M and 9.3% below the HD 6770M. This clustering around older hardware suggests that the single recorded benchmark result places this part in a very low performance tier, far removed from the Radeon 860M's standing.

The absence of overlapping benchmarks means the database cannot confirm a direct win for either part in a shared test. The wins count is zero for both sides. The performance gap suggested by the average scores and percentile ranks is substantial, but the different test methodologies prevent a rigorous head-to-head verdict from the recorded data alone.

Architecture Differences

Both parts share the same RDNA 3.5 architecture, the same 4 nm process node, and the same foundry, TSMC. This common foundation means the fundamental instruction set and hardware feature set are identical. Both list DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4 as supported APIs.

The GPU core configurations differ significantly. The AMD Radeon 860M uses the Krackan Point chip and is classified as part of the Navi III IGP (Strix Point Mobile) generation. It contains 512 shading units, 32 texture mapping units, 16 ROPs, and 8 ray tracing cores. The AMD Ryzen Z2 Extreme GPU uses the Strix Point chip, classified as a Console GPU (AMD), and doubles the core count in most areas: 1024 shading units, 64 TMUs, 48 ROPs, and 16 ray tracing cores. The Z2 Extreme GPU's ROP count is three times that of the 860M, which directly impacts pixel throughput.

Pixel and texture rates reflect these core differences. The Radeon 860M achieves 48.00 GPixel/s and 96.00 GTexel/s. The Ryzen Z2 Extreme GPU reaches 129.6 GPixel/s and 172.8 GTexel/s. Floating point performance shows a similar pattern: the 860M delivers 3.072 TFLOPS for both FP32 and FP16 (1:1), while the Z2 Extreme GPU delivers 5.530 TFLOPS for both, a substantial increase. Clock speeds differ in the opposite direction. The 860M has a base clock of 600 MHz and a boost clock of 3000 MHz. The Z2 Extreme GPU has a higher base clock of 800 MHz but a lower boost clock of 2700 MHz.

The transistor and die data only appears for the Z2 Extreme GPU. It uses 34,000 million transistors on a 233 mm² die, yielding a transistor density of 145.9M / mm². The 860M's transistor count and die size are recorded as unknown.

Memory handling separates the two parts clearly. The Radeon 860M uses system shared memory, with its memory size, type, bus width, and bandwidth all listed as system dependent. The Ryzen Z2 Extreme GPU has dedicated memory specifications: 16 GB of LPDDR5X on a 128 bit bus, with a bandwidth of 128.0 GB/s. Its memory clock is 1000 MHz with 8 Gbps effective speed. This represents a fixed memory subsystem for the Z2 Extreme GPU versus a flexible, system-dependent arrangement for the 860M.

Power characteristics also differ. The Radeon 860M has a TDP of 15 W, while the Z2 Extreme GPU has a TDP of 28 W. Both use no power connectors, and the 860M is an IGP with a PCIe 4.0 x8 bus interface. The Z2 Extreme GPU has no recorded bus interface or slot width. Display outputs differ as well: the 860M lists portable device dependent outputs, while the Z2 Extreme GPU lists a single USB Type-C output.

Where Each One Wins

The Radeon 860M wins on the basis of its recorded benchmark standing. Its 72nd percentile rank and average score of 26401 place it far above the Z2 Extreme GPU's 1st percentile and average score of 516. In any workload captured by the database's benchmark suite, the 860M's recorded results indicate a much higher performance tier. Its nearest rivals include discrete mobile and desktop GPUs like the GeForce MX550, RTX 5060, RX 5700 XT 50th Anniversary, and RTX A4000, with deltas between -1.1% and 0.3%. This suggests the 860M is competitive with those parts in average performance, making it suitable for demanding graphics tasks where those GPUs would be considered.

The Z2 Extreme GPU wins in specific silicon characteristics. Its shading unit count of 1024 is double the 860M's 512, its TMUs are double, and its ROPs are triple. Its FP32 and FP16 throughput of 5.530 TFLOPS exceeds the 860M's 3.072 TFLOPS by a wide margin. Its pixel rate of 129.6 GPixel/s and texture rate of 172.8 GTexel/s are both higher than the 860M's corresponding rates. The Z2 Extreme GPU also has dedicated 16 GB LPDDR5X memory with 128.0 GB/s bandwidth, which is not dependent on the host system's memory configuration. This fixed memory subsystem provides a known, consistent memory environment.

The use-case split follows these differences. For applications that rely on the database's recorded benchmark scores, the Radeon 860M is the stronger performer. For raw compute throughput and fill rates as specified in the architecture data, the Z2 Extreme GPU has the higher theoretical capability. The Z2 Extreme GPU's higher TDP of 28 W versus 15 W suggests it is designed for a different power envelope, likely a console-style fixed platform where sustained performance matters. The 860M's lower TDP and system shared memory indicate a more flexible integration into portable devices where power and memory allocation are dynamic.

The Z2 Extreme GPU's release date of 2025-07-08 is later than the 860M's 2025-02-28, and both are listed as active production parts. The 860M has a recorded predecessor, Navi II IGP, while the Z2 Extreme GPU has none. These timeline and lineage differences do not directly affect performance but contextualize the parts' positions in AMD's lineup.

FAQ

Q: Which GPU has a higher average benchmark score in the database?

A: The AMD Radeon 860M has an average benchmark score of 26401, while the AMD Ryzen Z2 Extreme GPU has an average score of 516. The 860M sits at the 72nd percentile, while the Z2 Extreme GPU sits at the 1st percentile.

Q: Do the two GPUs share any benchmark tests for direct comparison?

A: No. The database lists Geekbench OpenCL and Vulkan results for the Radeon 860M, while the Ryzen Z2 Extreme GPU has only a 3DMark Steel Nomad DX12 result. There are no overlapping tests, so a direct head-to-head benchmark comparison is not available.

Q: What are the core configuration differences between the two?

A: The Radeon 860M has 512 shading units, 32 TMUs, 16 ROPs, and 8 ray tracing cores. The Ryzen Z2 Extreme GPU has 1024 shading units, 64 TMUs, 48 ROPs, and 16 ray tracing cores. Both use RDNA 3.5 architecture on a 4 nm TSMC process.

Q: How do their memory systems differ?

A: The Radeon 860M uses system shared memory with a system dependent bus width and bandwidth. The Ryzen Z2 Extreme GPU has 16 GB of LPDDR5X memory on a 128 bit bus with 128.0 GB/s bandwidth and a memory clock of 1000 MHz (8 Gbps effective).

Q: Which GPU has higher theoretical compute throughput?

A: The Ryzen Z2 Extreme GPU has a higher FP32 and FP16 throughput of 5.530 TFLOPS, compared to 3.072 TFLOPS for the Radeon 860M. The Z2 Extreme GPU also has higher pixel rate (129.6 GPixel/s vs 48.00 GPixel/s) and texture rate (172.8 GTexel/s vs 96.00 GTexel/s).

Q: What are the power specifications for each GPU?

A: The Radeon 860M has a TDP of 15 W, while the Ryzen Z2 Extreme GPU has a TDP of 28 W. Neither uses power connectors, and both are active production parts.

Specification Differences

The two parts differ in the following recorded specifications:

| Specification | AMD Radeon 860M | AMD Ryzen Z2 Extreme GPU |

|----------------|-----------------|--------------------------|

| Chip | Krackan Point | Strix Point |

| Generation | Navi III IGP (Strix Point Mobile) | Console GPU (AMD) |

| Transistors | Unknown | 34,000 million |

| Die Size | Unknown | 233 mm² |

| Transistor Density | Not recorded | 145.9M / mm² |

| Base Clock | 600 MHz | 800 MHz |

| Boost Clock | 3000 MHz | 2700 MHz |

| Memory Clock | System Shared | 1000 MHz 8 Gbps effective |

| Memory Size | System Shared | 16 GB |

| Memory Type | System Shared | LPDDR5X |

| Memory Bus Width | System Shared | 128 bit |

| Memory Bandwidth | System Dependent | 128.0 GB/s |

| Shading Units | 512 | 1024 |

| TMUs | 32 | 64 |

| ROPs | 16 | 48 |

| Ray Tracing Cores | 8 | 16 |

| Pixel Rate | 48.00 GPixel/s | 129.6 GPixel/s |

| Texture Rate | 96.00 GTexel/s | 172.8 GTexel/s |

| FP32 | 3.072 TFLOPS | 5.530 TFLOPS |

| FP16 | 3.072 TFLOPS (1:1) | 5.530 TFLOPS (1:1) |

| TDP | 15 W | 28 W |

| Slot Width | IGP | Not recorded |

| Bus Interface | PCIe 4.0 x8 | Not recorded |

| Display Outputs | Portable Device Dependent | 1x USB Type-C |

| Release Date | 2025-02-28 | 2025-07-08 |

| Predecessor | Navi II IGP | None |

Both parts share the same manufacturer (AMD), architecture (RDNA 3.5), process node (4 nm), foundry (TSMC), API support (DirectX 12 Ultimate 12_2, OpenGL 4.6, Vulkan 1.4), power connector configuration (None), and production status (Active). Neither has a recorded launch MSRP, tensor core count, suggested PSU, or physical dimensions.