AMD Xbox Series X 6nm GPU vs Intel Arc B390 Comparison

# FAQ

Q: What is the architectural generation of each GPU?

A: The AMD Xbox Series X 6nm GPU uses the RDNA 2.0 architecture, built on TSMC's 6 nm process with 15,300 million transistors. The Intel Arc B390 uses the Xe3-LPG architecture, built on Intel's 3 nm process.

Q: How do the shading unit counts compare?

A: The AMD Xbox Series X 6nm GPU has 3,328 shading units, 208 texture mapping units, and 64 render output units. The Intel Arc B390 has 1,536 shading units, 48 texture mapping units, and 24 render output units.

Q: What is the memory configuration of each?

A: The AMD Xbox Series X 6nm GPU has 10 GB of GDDR6 memory on a 320 bit bus, delivering 560.0 GB/s bandwidth. The Intel Arc B390 uses system shared memory with system dependent bandwidth.

Q: Which GPU has a higher FP32 compute throughput?

A: The AMD Xbox Series X 6nm GPU delivers 12.15 TFLOPS FP32, while the Intel Arc B390 delivers 7.680 TFLOPS FP32. The AMD part is approximately 58% higher in this metric.

Q: What is the power consumption difference?

A: The AMD Xbox Series X 6nm GPU has a 200 W TDP, while the Intel Arc B390 has an 80 W TDP. The Intel part consumes 120 W less according to the recorded specifications.

Q: What benchmark data exists for each GPU?

A: The AMD Xbox Series X 6nm GPU has no recorded benchmark scores in the database, with an average benchmark score of 0 and a percentile of 50. The Intel Arc B390 has one recorded score of 1,482 in 3DMark Steel Nomad DX12, placing it at the 9th percentile.

# Architecture Differences

The two GPUs represent fundamentally different design philosophies. The AMD Xbox Series X 6nm GPU is a console-focused discrete graphics solution built on RDNA 2.0, while the Intel Arc B390 is an integrated graphics processor (IGP) within Intel's Panther Lake mobile platform using Xe3-LPG architecture.

The process technology differs significantly. AMD uses TSMC's 6 nm node with 15,300 million transistors, whereas Intel uses its own 3 nm process. The AMD chip, codenamed Scarlett 6nm, has a known transistor count, but the Intel part's transistor count is not recorded. The die size for both is unknown.

The memory architecture is a major differentiator. The AMD GPU includes 10 GB of dedicated GDDR6 memory on a 320 bit interface with 560.0 GB/s bandwidth. The Intel Arc B390 instead relies on system shared memory, meaning its bandwidth is system dependent and its memory type is not dedicated. This affects how each GPU accesses data during rendering.

The compute resources differ substantially. AMD provides 3,328 shading units, 208 TMUs, and 64 ROPs. Intel provides 1,536 shading units, 48 TMUs, and 24 ROPs. The AMD GPU has no dedicated ray tracing core count listed, while the Intel Arc B390 includes 12 ray tracing cores.

Clock behavior also differs. The AMD GPU lists only a memory clock of 1750 MHz (14 Gbps effective), with no base or boost clock recorded. The Intel Arc B390 has a base clock of 300 MHz and a boost clock of 2500 MHz, reflecting its integrated nature where power management can ramp clocks dynamically.

API support is similar but not identical. Both support DirectX 12 Ultimate (12_2) and OpenGL 4.6. The AMD GPU supports Vulkan 1.2, while the Intel Arc B390 supports Vulkan 1.4. The Intel part also has a higher Vulkan version, which may affect compatibility with newer applications using that API.

# The Verdict

The data presents a clear performance hierarchy, but the comparison is complicated by the absence of benchmark results for the AMD GPU. The AMD Xbox Series X 6nm GPU has no recorded benchmark scores, so its measured performance cannot be directly compared to the Intel Arc B390's single score of 1,482 in 3DMark Steel Nomad DX12.

Based on specifications alone, the AMD GPU holds advantages in shading units, texture units, render output units, FP32 throughput, and dedicated memory bandwidth. The Intel Arc B390 counters with a lower TDP of 80 W versus 200 W, a smaller process node at 3 nm versus 6 nm, and integrated form factor with no power connectors required.

The percentile rankings place the Intel Arc B390 at the 9th percentile among all GPUs, with its nearest rivals being low-end NVIDIA parts. The NVIDIA GeForce GT 520MX scores 1,463 (1.3% lower), the GeForce 800M scores 1,460 (1.5% lower), the GeForce GT 625 OEM scores 1,446 (2.5% lower), and the GeForce GT 710 scores 1,443 (2.7% lower). This indicates the Intel part sits at the entry level of measured performance.

The AMD GPU's 50th percentile ranking, despite having no benchmark scores, reflects its classification in the database rather than measured results. Users should interpret this as a placeholder rather than a verified performance metric.

The choice between these two depends on the intended use case. The AMD Xbox Series X 6nm GPU is designed for a console environment with dedicated graphics memory and high compute throughput. The Intel Arc B390 is an integrated solution for mobile devices where power efficiency and space are priorities.

# Specification Differences

The recorded specifications show differences across nearly every category.

Process and Foundry: AMD uses TSMC's 6 nm process; Intel uses its own 3 nm process.

Transistors: AMD has 15,300 million; Intel's transistor count is not recorded.

Clocks: AMD lists a memory clock of 1750 MHz (14 Gbps effective) but no base or boost clocks. Intel has a base clock of 300 MHz and a boost clock of 2500 MHz.

Memory: AMD has 10 GB GDDR6 on a 320 bit bus with 560.0 GB/s bandwidth. Intel uses system shared memory with system dependent bandwidth.

Compute Units: AMD has 3,328 shading units, 208 TMUs, and 64 ROPs. Intel has 1,536 shading units, 48 TMUs, and 24 ROPs.

Ray Tracing: AMD lists no dedicated RT core count. Intel includes 12 RT cores.

Rates: AMD delivers 116.8 GPixel/s pixel rate and 379.6 GTexel/s texture rate. Intel delivers 60.00 GPixel/s pixel rate and 120.0 GTexel/s texture rate.

FP32: AMD delivers 12.15 TFLOPS. Intel delivers 7.680 TFLOPS.

FP16: AMD delivers 24.29 TFLOPS (2:1). Intel delivers 15.36 TFLOPS (2:1).

TDP: AMD is rated at 200 W. Intel is rated at 80 W.

Form Factor: AMD is a discrete card with dimensions of 301 mm length, 151 mm height, and 151 mm width. Intel is an IGP with no dimensions recorded and no power connectors.

Display Outputs: AMD has 1x HDMI 2.1. Intel's outputs are portable device dependent.

Bus Interface: AMD has no bus interface recorded. Intel uses IGP.

Vulkan: AMD supports 1.2. Intel supports 1.4.

Release Date: AMD released on 2024-10-14. Intel releases on 2026-01-26.

Launch MSRP: AMD has a launch MSRP of 599 USD. Intel has no recorded launch MSRP.

# Head-to-Head Benchmarks

The database contains no direct head-to-head benchmark results between these two GPUs. The wins counter shows 0 for both sides. However, the Intel Arc B390 has a single recorded benchmark score that can be examined.

In 3DMark Steel Nomad DX12, the Intel Arc B390 scores 1,482. Its nearest rivals in the database are all NVIDIA entry-level parts. The GeForce GT 520MX scores 1,463, which is 1.3% lower. The GeForce 800M scores 1,460, 1.5% lower. The GeForce GT 625 OEM scores 1,446, 2.5% lower. The GeForce GT 710 scores 1,443, 2.7% lower.

This places the Intel Arc B390 at the 9th percentile among all GPUs, meaning 91% of recorded GPUs score higher. The performance level is consistent with very old or very low-end discrete graphics solutions.

The AMD Xbox Series X 6nm GPU has no benchmark entries in the database. Its average benchmark score is recorded as 0, and its percentile is 50, which appears to be a neutral default value rather than a measured result. Without recorded scores, no quantitative comparison can be made from direct measurements.

The specification data provides a proxy for expected performance differences. The AMD GPU's FP32 throughput of 12.15 TFLOPS is 58% higher than the Intel part's 7.680 TFLOPS. The pixel rate of 116.8 GPixel/s is 95% higher than the Intel part's 60.00 GPixel/s. The texture rate of 379.6 GTexel/s is more than triple the Intel part's 120.0 GTexel/s.

Memory bandwidth presents the largest gap. The AMD GPU's 560.0 GB/s dedicated bandwidth versus the Intel part's system dependent bandwidth means the AMD GPU has a guaranteed minimum bandwidth, while the Intel part's performance will vary based on the host system's memory configuration.

# Where Each One Wins

AMD Xbox Series X 6nm GPU wins in raw compute throughput. The 12.15 TFLOPS FP32 and 24.29 TFLOPS FP16 figures are substantially higher than the Intel Arc B390's 7.680 TFLOPS and 15.36 TFLOPS. This suggests advantages in workloads that scale with shader count, such as high-resolution rendering and complex pixel shaders.

AMD Xbox Series X 6nm GPU wins in memory bandwidth. The dedicated 560.0 GB/s over a 320 bit bus is a fixed resource, whereas the Intel Arc B390 depends on system shared memory with system dependent bandwidth. Games and applications that stream large textures will benefit from the guaranteed bandwidth.

AMD Xbox Series X 6nm GPU wins in texture and pixel throughput. The 379.6 GTexel/s texture rate and 116.8 GPixel/s pixel rate are both significantly higher than the Intel part's 120.0 GTexel/s and 60.00 GPixel/s. This indicates better performance in fill-rate bound scenarios.

Intel Arc B390 wins in power efficiency. The 80 W TDP versus 200 W means the Intel part consumes 120 W less. For mobile or compact systems where thermal and power budgets are constrained, this is a decisive advantage.

Intel Arc B390 wins in process technology. The 3 nm process from Intel is smaller than AMD's 6 nm process from TSMC. This contributes to the lower power draw and potentially smaller physical footprint, though the AMD GPU's discrete card dimensions of 301 mm by 151 mm by 151 mm are recorded, while the Intel IGP has no dimensions.

Intel Arc B390 wins in ray tracing core availability. The Intel part has 12 dedicated ray tracing cores, while the AMD GPU has no RT core count recorded. This may affect ray-traced workloads, though the overall compute disadvantage may limit practical impact.

Intel Arc B390 wins in API version support. Vulkan 1.4 support versus Vulkan 1.2 means the Intel part is aligned with newer API revisions. Both support DirectX 12 Ultimate (12_2) and OpenGL 4.6.

Intel Arc B390 wins in measured benchmark standing. The single recorded score of 1,482 in 3DMark Steel Nomad DX12 places it above its nearest recorded rivals by margins of 1.3% to 2.7%. The AMD GPU has no measured scores in the database.