AMD Ryzen Z1 Extreme GPU vs Intel Arc Pro B60 Dual Comparison

Where Each One Wins

The benchmark data records no direct head-to-head wins for either part, which is itself informative. The AMD Ryzen Z1 Extreme GPU and the Intel Arc Pro B60 Dual occupy entirely separate performance tiers, so the use-case split is defined by the specification sheet rather than by measured competition. The AMD part is a 30 W mobile-class component built for embedded or handheld contexts, while the Intel part is a 400 W professional desktop accelerator. Neither part has a single recorded benchmark victory over the other in the database, because no shared workload has been run against both.

The AMD Ryzen Z1 Extreme GPU wins in scenarios that demand minimal power draw and a compact physical footprint. Its 30 W TDP, 280 mm length, and 21 mm width make it suitable for constrained chassis designs. The 16 GB of LPDDR5 memory is soldered in the Phoenix package, and the single USB Type-C display output indicates a device intended for a single-panel or VR-style use case. The Intel Arc Pro B60 Dual wins in scenarios that demand high throughput and large memory capacity. Its 24 GB of GDDR6 memory on a 192-bit bus delivers 456.0 GB/s of bandwidth, roughly nine times the AMD part's 51.20 GB/s. The 80 ROPs and 160 TMUs give it a large advantage in fill-rate-bound work, and the 4x mini-DisplayPort 2.1 outputs support multi-monitor professional setups.

The data suggests a clean split: the AMD part is for low-power integrated-style deployments, the Intel part is for workstation rendering, compute, and multi-display output. The absence of shared benchmarks means the database cannot assign a win count, but the architectural numbers point to entirely different application spaces.

Architecture Differences

The two GPUs come from different foundries, nodes, and design philosophies. The AMD Ryzen Z1 Extreme GPU uses the Phoenix chip built on TSMC's 4 nm process, with 25,390 million transistors on a 178 mm² die. The Intel Arc Pro B60 Dual uses the BMG-G21 chip built on TSMC's 5 nm process, with 19,600 million transistors on a 272 mm² die. The AMD part achieves a transistor density of 142.6M per mm², while the Intel part reaches 72.1M per mm². That density gap reflects the node difference: the 4 nm process packs more transistors into less area, which helps explain the AMD part's low 30 W power envelope.

Architecturally, the AMD part uses RDNA 3.0, while the Intel part uses Xe2-HPG from the Battlemage Pro Series. The AMD part belongs to the Console GPU generation, the Intel part to a professional workstation generation. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, so API-level feature parity holds.

The Intel part has 2560 shading units, 160 TMUs, 80 ROPs, and 20 RT cores. The AMD part has 768 shading units, 48 TMUs, 32 ROPs, and 12 RT cores. The Intel part more than triples the AMD part in shading units and TMUs, and it doubles the ROP count. The RT core count favors Intel by 20 to 12. Neither part lists tensor cores in the database.

Memory architecture differs fundamentally. The AMD part uses 16 GB of LPDDR5 on a 64-bit bus, with memory clocked at 800 MHz and 6.4 Gbps effective. The Intel part uses 24 GB of GDDR6 on a 192-bit bus, with memory clocked at 2375 MHz and 19 Gbps effective. The bus width difference (64-bit versus 192-bit) is the primary driver of the bandwidth gap. The AMD part's memory is part of a unified Phoenix package, consistent with its console-oriented design; the Intel part is a discrete dual-slot card with a 16-pin power connector and an 800 W suggested PSU.

Cooling and power delivery diverge sharply. The AMD part has no power connectors and a 30 W TDP. The Intel part is dual-slot, requires a single 16-pin connector, and carries a 400 W TDP with an 800 W suggested PSU. The AMD part is 280 mm long, 111 mm tall, and 21 mm wide. The Intel part is 300 mm long, 110 mm tall, and 40 mm wide. The Intel card is 19 mm thicker, a direct consequence of its dual-slot cooler.

Head-to-Head Benchmarks

The database contains no recorded head-to-head benchmark results between these two parts. The winsA and winsB counters are both zero, and the headToHeadBenchmarks array is empty. Consequently, there are no exact score deltas to report. The comparison must be built from the recorded specification fields, which still provide concrete numbers.

The largest measured gap in the data is memory bandwidth: 456.0 GB/s for the Intel part versus 51.20 GB/s for the AMD part. That is an 8.9x difference. For workloads that stream large textures or geometry, the Intel part has a decisive advantage. Pixel throughput follows the same pattern: the Intel part delivers 192.0 GPixel/s against 86.40 GPixel/s for the AMD part, a 2.2x advantage. Texture throughput shows the biggest ratio: 384.0 GTexel/s versus 129.6 GTexel/s, a 2.96x advantage for Intel.

Compute throughput favors Intel as well. The Intel part delivers 12.29 TFLOPS FP32 against 8.294 TFLOPS for the AMD part, a 1.48x advantage. FP16 figures are 24.58 TFLOPS versus 16.59 TFLOPS, again a 1.48x ratio, since both parts use a 2:1 FP16 rate. Clock behavior differs: the AMD part has a lower base clock (800 MHz) but a higher boost clock (2700 MHz), while the Intel part has a higher base clock (2000 MHz) and a lower boost clock (2400 MHz). The AMD part's boost exceeds its base by 1900 MHz, indicating a wide dynamic range for power management. The Intel part's boost exceeds its base by only 400 MHz, reflecting a steadier operating point under a 400 W envelope.

The AMD part does hold advantages in a few recorded fields. It uses a smaller die (178 mm² versus 272 mm²), packs more transistors (25,390 million versus 19,600 million), and runs on a newer process node (4 nm versus 5 nm). Its transistor density is roughly double that of the Intel part. The AMD part also has a lower TDP by a factor of more than 13 (30 W versus 400 W), which makes it deployable in systems where the Intel part would require substantial power delivery and cooling.

Specification Differences

The two parts differ in every major specification category. Process node: AMD uses 4 nm, Intel uses 5 nm, both from TSMC. Transistor count: AMD has 25,390 million, Intel has 19,600 million. Die size: AMD is 178 mm², Intel is 272 mm². Transistor density: AMD is 142.6M per mm², Intel is 72.1M per mm².

Clock speeds: AMD base is 800 MHz, boost is 2700 MHz; Intel base is 2000 MHz, boost is 2400 MHz. Memory clock: AMD runs at 800 MHz with 6.4 Gbps effective; Intel runs at 2375 MHz with 19 Gbps effective. Memory size: AMD has 16 GB LPDDR5, Intel has 24 GB GDDR6. Bus width: AMD is 64-bit, Intel is 192-bit. Bandwidth: AMD is 51.20 GB/s, Intel is 456.0 GB/s.

Compute units: AMD has 768 shading units, 48 TMUs, 32 ROPs, 12 RT cores; Intel has 2560 shading units, 160 TMUs, 80 ROPs, 20 RT cores. Pixel rate: AMD is 86.40 GPixel/s, Intel is 192.0 GPixel/s. Texture rate: AMD is 129.6 GTexel/s, Intel is 384.0 GTexel/s. FP32: AMD is 8.294 TFLOPS, Intel is 12.29 TFLOPS. FP16: AMD is 16.59 TFLOPS, Intel is 24.58 TFLOPS.

TDP: AMD is 30 W, Intel is 400 W. Slot width: AMD has none listed, Intel is dual-slot. Power connectors: AMD has none, Intel has one 16-pin. Suggested PSU: AMD has none listed, Intel is 800 W. Bus interface: AMD has none listed, Intel is PCIe 5.0 x8. Display outputs: AMD has one USB Type-C, Intel has four mini-DisplayPort 2.1.

Dimensions: AMD is 280 mm by 111 mm by 21 mm; Intel is 300 mm by 110 mm by 40 mm. Release date: AMD launched on 2023-06-12, Intel on 2025-09-04. Launch MSRP: AMD is 699 USD, Intel is 1,199 USD. Both parts are Active in production, both sit at the 50th percentile against all GPUs in the database, and neither has any nearest rivals recorded.

FAQ

Q: Which GPU has more memory bandwidth?

A: The Intel Arc Pro B60 Dual has 456.0 GB/s, versus 51.20 GB/s for the AMD Ryzen Z1 Extreme GPU. The Intel part uses a 192-bit GDDR6 bus while the AMD part uses a 64-bit LPDDR5 bus.

Q: What is the TDP difference between the two?

A: The AMD Ryzen Z1 Extreme GPU has a 30 W TDP and no power connectors. The Intel Arc Pro B60 Dual has a 400 W TDP, requires a single 16-pin power connector, and lists an 800 W suggested PSU.

Q: Do both support the same graphics APIs?

A: Yes. Both parts support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Q: Which GPU has more shading units?

A: The Intel Arc Pro B60 Dual has 2560 shading units, while the AMD Ryzen Z1 Extreme GPU has 768. The Intel part also has 20 RT cores versus 12, 160 TMUs versus 48, and 80 ROPs versus 32.

Q: What are the launch dates?

A: The AMD Ryzen Z1 Extreme GPU launched on 2023-06-12. The Intel Arc Pro B60 Dual launched on 2025-09-04.

Q: Which GPU has a higher boost clock?

A: The AMD Ryzen Z1 Extreme GPU has a boost clock of 2700 MHz, higher than the Intel Arc Pro B60 Dual's 2400 MHz. The Intel part has a higher base clock at 2000 MHz versus 800 MHz.

The Verdict

The recorded data supports a direct conclusion: these are not competing products. The AMD Ryzen Z1 Extreme GPU is a 30 W, 16 GB LPDDR5 part with a single USB Type-C output, built for low-power embedded or handheld systems. The Intel Arc Pro B60 Dual is a 400 W, 24 GB GDDR6 workstation card with four mini-DisplayPort 2.1 outputs, built for professional rendering and multi-display compute.

Anyone constrained by power, thermal, or physical space should select the AMD part. Its 30 W TDP, 21 mm width, and 178 mm² die make it the only viable choice for compact or battery-powered designs. Its 2700 MHz boost clock and 8.294 TFLOPS FP32 provide reasonable throughput for that power class.

Anyone needing raw throughput, memory capacity, or output flexibility should select the Intel part. Its 12.29 TFLOPS FP32, 456.0 GB/s bandwidth, 24 GB memory, and 4x mini-DisplayPort 2.1 outputs place it in a different performance class entirely. The 400 W TDP and 800 W suggested PSU are the cost of that capability. The data shows no overlap in application targets, and no head-to-head benchmark exists to reconcile them.