AMD Radeon 860M vs AMD Ryzen Z1 Extreme GPU Comparison

The Verdict

The database comparison between the AMD Radeon 860M and the AMD Ryzen Z1 Extreme GPU shows two distinctly different integrated graphics solutions, each with a clear target platform. The Radeon 860M, built on the Krackan Point chip with RDNA 3.5 architecture, is a 15 W IGP designed for portable devices, delivering a measured average benchmark score of 26401 across Geekbench OpenCL and Vulkan tests. The Ryzen Z1 Extreme GPU, part of the Phoenix chip with RDNA 3.0 architecture, is a 30 W console-class part with a 16 GB LPDDR5 memory pool and a 280 mm board length, indicating it is intended for handheld gaming consoles rather than general-purpose laptops.

Benchmark data for the Radeon 860M places it at the 72nd percentile among all GPUs, with its average score of 26401 sitting within 1.1% of several discrete desktop and mobile parts, including the NVIDIA RTX A4000 (26683, delta -1.1%) and the AMD Radeon RX 5700 XT 50th Anniversary (26553, delta -0.6%). The Ryzen Z1 Extreme GPU has no recorded benchmark scores in the database, so its percentile stands at 50 and its average score at 0, meaning direct numerical comparison of compute performance is not possible from recorded data.

The verdict from the available data is straightforward: the Radeon 860M is the part with proven, measured performance in synthetic workloads, while the Ryzen Z1 Extreme GPU offers substantially higher raw specifications, including 768 shading units versus 512, 48 texture mapping units versus 32, and 8.294 TFLOPS FP32 versus 3.072 TFLOPS. The Z1 Extreme GPU also carries a launch MSRP of 699 USD. For users seeking a low-power integrated GPU in a thin-and-light device, the 860M is the data-supported choice. For those needing maximum integrated graphics throughput in a handheld form factor, the Z1 Extreme GPU's specification sheet is decisively stronger, though the database lacks benchmark confirmation of that advantage.

Architecture Differences

The architectural split between these two AMD parts is significant, as they belong to different RDNA generations. The Radeon 860M uses RDNA 3.5, the newer iteration, built on the Krackan Point chip, and is categorized under the Navi III IGP generation for Strix Point Mobile. The Ryzen Z1 Extreme GPU uses RDNA 3.0 on the Phoenix chip, classified as a console GPU. Both parts are fabricated on the same 4 nm TSMC process, so process node does not differentiate them.

The compute configuration differs sharply. The Radeon 860M has 512 shading units, 32 TMUs, 16 ROPs, and 8 ray tracing cores. The Ryzen Z1 Extreme GPU doubles some of these resources: it has 768 shading units, 48 TMUs, 32 ROPs, and 12 ray tracing cores. This means the Z1 Extreme GPU has 50% more shading units, 50% more TMUs, double the ROPs, and 50% more RT cores compared to the 860M. The Z1 Extreme GPU also has a documented transistor count of 25,390 million on a 178 mm² die, yielding a density of 142.6 million transistors per mm², while the 860M's transistor count and die size are listed as unknown.

Clock behavior also diverges. The Radeon 860M runs at a 600 MHz base clock and boosts to 3000 MHz. The Ryzen Z1 Extreme GPU starts higher at 800 MHz base but boosts to only 2700 MHz. Despite the lower boost clock, the Z1 Extreme GPU's larger shader array produces far higher throughput: its FP32 rate is 8.294 TFLOPS versus 3.072 TFLOPS for the 860M, a factor of 2.7. The FP16 rates differ even more dramatically: the Z1 Extreme GPU achieves 16.59 TFLOPS with a 2:1 ratio, while the 860M manages 3.072 TFLOPS at a 1:1 ratio, meaning the Z1 Extreme GPU has no FP16 advantage beyond its raw shader count.

Memory architecture is another major divider. The Radeon 860M uses system-shared memory with system-dependent bandwidth, typical for a laptop IGP. The Ryzen Z1 Extreme GPU has a dedicated 16 GB LPDDR5 pool on a 64-bit bus, delivering 51.20 GB/s bandwidth and a memory clock of 800 MHz with 6.4 Gbps effective. This fixed memory configuration is a console-style design, whereas the 860M relies entirely on the host system's RAM.

Head-to-Head Benchmarks

Direct head-to-head benchmark results between the Radeon 860M and the Ryzen Z1 Extreme GPU are not recorded in the database, as the headToHeadBenchmarks array is empty and both win counts are zero. However, the Radeon 860M has two individual Geekbench scores: 22759 in OpenCL and 30043 in Vulkan. These produce an average benchmark score of 26401. The Ryzen Z1 Extreme GPU has no benchmark entries, so no score exists to compare directly.

The Radeon 860M's nearest rivals provide context for its measured performance. Its average score of 26401 is within 0.1% of the NVIDIA GeForce MX550 (26421, delta -0.1%), meaning the two are statistically tied. It is also 0.3% ahead of the NVIDIA GeForce RTX 5060 (26331), 0.6% behind the AMD Radeon RX 5700 XT 50th Anniversary (26553), and 1.1% behind the NVIDIA RTX A4000 (26683). These deltas indicate that the 860M sits in a tight cluster of discrete GPUs from both NVIDIA and AMD, despite being an integrated part with a 15 W TDP.

The Vulkan score of 30043 is notably higher than the OpenCL score of 22759, a gap of 7284 points, suggesting the 860M's RDNA 3.5 architecture performs substantially better under the Vulkan API in the recorded workload. The percentile placement at 72 among all GPUs reinforces that this IGP outperforms a majority of the GPU database, including many discrete parts.

Since the Ryzen Z1 Extreme GPU lacks benchmark records, the only head-to-head inference available comes from specification comparison. The Z1 Extreme GPU's FP32 throughput of 8.294 TFLOPS is 2.7 times the 860M's 3.072 TFLOPS. Its pixel rate of 86.40 GPixel/s is 1.8 times the 860M's 48.00 GPixel/s, and its texture rate of 129.6 GTexel/s is 1.35 times the 860M's 96.00 GTexel/s. These specification advantages are substantial, but without recorded benchmark scores, they remain theoretical rather than measured.

Specification Differences

The following specification fields differ between the two parts:

• Chip: Krackan Point (860M) vs Phoenix (Z1 Extreme)
• Architecture: RDNA 3.5 (860M) vs RDNA 3.0 (Z1 Extreme)
• Generation: Navi III IGP (Strix Point Mobile) (860M) vs Console GPU (AMD) (Z1 Extreme)
• Transistors: unknown (860M) vs 25,390 million (Z1 Extreme)
• Die Size: unknown (860M) vs 178 mm² (Z1 Extreme)
• Transistor Density: null (860M) vs 142.6M / mm² (Z1 Extreme)
• Base Clock: 600 MHz (860M) vs 800 MHz (Z1 Extreme)
• Boost Clock: 3000 MHz (860M) vs 2700 MHz (Z1 Extreme)
• Memory Clock: System Shared (860M) vs 800 MHz, 6.4 Gbps effective (Z1 Extreme)
• Memory Size: System Shared (860M) vs 16 GB (Z1 Extreme)
• Memory Type: System Shared (860M) vs LPDDR5 (Z1 Extreme)
• Memory Bus Width: System Shared (860M) vs 64 bit (Z1 Extreme)
• Memory Bandwidth: System Dependent (860M) vs 51.20 GB/s (Z1 Extreme)
• Shading Units: 512 (860M) vs 768 (Z1 Extreme)
• TMUs: 32 (860M) vs 48 (Z1 Extreme)
• ROPs: 16 (860M) vs 32 (Z1 Extreme)
• RT Cores: 8 (860M) vs 12 (Z1 Extreme)
• Pixel Rate: 48.00 GPixel/s (860M) vs 86.40 GPixel/s (Z1 Extreme)
• Texture Rate: 96.00 GTexel/s (860M) vs 129.6 GTexel/s (Z1 Extreme)
• FP32: 3.072 TFLOPS (860M) vs 8.294 TFLOPS (Z1 Extreme)
• FP16: 3.072 TFLOPS (1:1) (860M) vs 16.59 TFLOPS (2:1) (Z1 Extreme)
• TDP: 15 W (860M) vs 30 W (Z1 Extreme)
• Slot Width: IGP (860M) vs null (Z1 Extreme)
• Bus Interface: PCIe 4.0 x8 (860M) vs null (Z1 Extreme)
• Display Outputs: Portable Device Dependent (860M) vs 1x USB Type-C (Z1 Extreme)
• Dimensions: null (860M) vs 280 mm length, 111 mm height, 21 mm width (Z1 Extreme)
• Release Date: 2025-02-28 (860M) vs 2023-06-12 (Z1 Extreme)
• Predecessor: Navi II IGP (860M) vs null (Z1 Extreme)
• Launch MSRP: null (860M) vs 699 USD (Z1 Extreme)
• Benchmark Scores: 22759 OpenCL, 30043 Vulkan (860M) vs none (Z1 Extreme)
• Percentile vs All GPUs: 72 (860M) vs 50 (Z1 Extreme)
• Average Benchmark Score: 26401 (860M) vs 0 (Z1 Extreme)

Fields that are identical include manufacturer (AMD), process node (4 nm), foundry (TSMC), power connectors (None), DirectX support (12 Ultimate, 12_2), OpenGL (4.6), Vulkan (1.4), and production status (Active).

FAQ

Q: Which GPU has better measured benchmark performance?

A: The AMD Radeon 860M is the only one of the two with recorded scores. It achieves 22759 in Geekbench OpenCL and 30043 in Geekbench Vulkan, for an average of 26401. The AMD Ryzen Z1 Extreme GPU has no benchmark entries in the database, so no measured comparison is possible.

Q: How does the Radeon 860M compare to its nearest rivals?

A: The 860M's average score of 26401 is within 0.1% of the NVIDIA GeForce MX550 (26421), 0.3% ahead of the NVIDIA GeForce RTX 5060 (26331), 0.6% behind the AMD Radeon RX 5700 XT 50th Anniversary (26553), and 1.1% behind the NVIDIA RTX A4000 (26683).

Q: What is the main architectural difference between the two?

A: The Radeon 860M uses RDNA 3.5 on the Krackan Point chip, while the Ryzen Z1 Extreme GPU uses RDNA 3.0 on the Phoenix chip. Both are 4 nm TSMC parts, but the Z1 Extreme GPU has 768 shading units, 48 TMUs, 32 ROPs, and 12 RT cores versus 512 shading units, 32 TMUs, 16 ROPs, and 8 RT cores for the 860M.

Q: How do their memory configurations differ?

A: The Radeon 860M uses system-shared memory with system-dependent bandwidth. The Ryzen Z1 Extreme GPU has a fixed 16 GB LPDDR5 pool on a 64-bit bus, delivering 51.20 GB/s bandwidth at an 800 MHz memory clock with 6.4 Gbps effective.

Q: Which part has a higher boost clock?

A: The Radeon 860M boosts to 3000 MHz, which is higher than the Ryzen Z1 Extreme GPU's 2700 MHz boost. However, the Z1 Extreme GPU has a higher base clock at 800 MHz versus 600 MHz for the 860M.

Q: What are the physical and power differences?

A: The Radeon 860M is an IGP with a 15 W TDP and PCIe 4.0 x8 interface. The Ryzen Z1 Extreme GPU has a 30 W TDP, measures 280 mm by 111 mm by 21 mm, and has a 1x USB Type-C display output. The Z1 Extreme GPU also has a documented die size of 178 mm² with 25,390 million transistors, while the 860M's die data is unknown.