Intel Arc B390 vs Intel Data Center GPU Max 1350 Comparison

Head-to-Head Benchmarks

The benchmark data available for these two Intel GPUs is highly asymmetrical. The Intel Arc B390 has a recorded 3DMark Steel Nomad DX12 score of 1482, placing it in the 9th percentile of all GPUs in the database. The Intel Data Center GPU Max 1350 has no recorded benchmark scores, leaving its average benchmark score at 0 and its percentile at 50, which reflects its position in the middle of the distribution due to the absence of tested data rather than measured performance.

The Arc B390's score of 1482 positions it narrowly ahead of several legacy NVIDIA parts. It shows a 1.3% delta over the NVIDIA GeForce GT 520MX, which scores 1463, a 1.5% delta over the NVIDIA GeForce 800M at 1460, a 2.5% delta over the NVIDIA GeForce GT 625 OEM at 1446, and a 2.7% delta over the NVIDIA GeForce GT 710 at 1443. These margins are small, indicating that the Arc B390 delivers performance in the same tier as those older discrete mobile and entry-level desktop parts. The data does not support a direct numerical comparison between the Arc B390 and the Data Center GPU Max 1350, as no head-to-head benchmark results exist in the database.

The Data Center GPU Max 1350 does not have a single benchmark entry in the database. Its average benchmark score is listed as 0, and there are no nearest rivals recorded for it. The Arc B390, by contrast, has a defined benchmark footprint, albeit a modest one. The absence of data for the Data Center GPU Max 1350 means the database cannot confirm any performance advantage for either product in a direct comparison. The Arc B390's 1482 score is the only measurable performance point available.

Architecture Differences

The architectural split between these two Intel parts is stark. The Intel Arc B390 uses the Panther Lake chip with the Xe3-LPG architecture, belonging to the Arc Graphics-M (Panther Lake) generation. It is built on a 3 nm process node at Intel's foundry. The Intel Data Center GPU Max 1350 uses the Ponte Vecchio chip with Generation 12.5 architecture, belonging to the Data Center GPU (Ponte Vecchio) generation, and is fabricated on a 10 nm process node, also at Intel's foundry.

Transistor counts and die sizes diverge dramatically. The Data Center GPU Max 1350 packs 100,000 million transistors on a 1280 mm² die, with a transistor density of 78.1 million transistors per square millimeter. The Arc B390's transistor count and die size are listed as unknown in the database, so no comparative figure can be stated.

Core configurations differ by an order of magnitude. The Arc B390 has 1536 shading units, 48 texture mapping units, 24 raster output units, and 12 ray tracing cores. The Data Center GPU Max 1350 has 14336 shading units, 896 texture mapping units, 0 raster output units, and 112 ray tracing cores. The Data Center part has no ROPs, which aligns with its compute-focused design, while the Arc B390 retains a conventional graphics pipeline with 24 ROPs.

Clock speeds show a trade-off between efficiency and throughput. The Arc B390 runs at a base clock of 300 MHz and a boost clock of 2500 MHz. The Data Center GPU Max 1350 runs at a base clock of 750 MHz and a boost clock of 1550 MHz. The Arc part boosts significantly higher, while the Data Center part has a higher base clock.

Memory architecture is fundamentally different. The Arc B390 uses system-shared memory, with its size, type, bus width, and bandwidth all listed as system dependent. The Data Center GPU Max 1350 has 96 GB of HBM2e memory on an 8192-bit bus, delivering 2.46 TB/s of bandwidth. Its memory clock is 1200 MHz, or 2.4 Gbps effective.

Compute throughput figures reflect the Data Center part's scale. The Arc B390 delivers 7.680 TFLOPS of FP32 performance and 15.36 TFLOPS of FP16 performance at a 2:1 ratio. The Data Center GPU Max 1350 delivers 44.44 TFLOPS of FP32 and 44.44 TFLOPS of FP16 at a 1:1 ratio. The Data Center part's FP16 rate matches its FP32 rate, indicating full-rate half-precision execution. The Arc B390's texture rate is 120.0 GTexel/s and its pixel rate is 60.00 GPixel/s. The Data Center GPU Max 1350's texture rate is 1,388.8 GTexel/s, while its pixel rate is 0 MPixel/s due to the absence of ROPs.

Power and physical specifications reinforce the different design goals. The Arc B390 has a TDP of 80 W, uses an IGP slot width, requires no power connectors, and connects via an IGP bus interface. The Data Center GPU Max 1350 has a TDP of 450 W, uses an OAM Module slot width, and connects via PCIe 5.0 x16. Its suggested PSU rating is 850 W.

API support also differs. The Arc B390 supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The Data Center GPU Max 1350 supports DirectX 12 (12_1) and OpenGL 4.6, but has no listed Vulkan support. Display outputs also diverge: the Arc B390's outputs are portable device dependent, while the Data Center GPU Max 1350 has no outputs at all.

The Verdict

The data points to two entirely different products with no overlapping use cases. The Intel Arc B390 is an integrated graphics solution with a modest 1482 Steel Nomad score, placing it in the 9th percentile of all GPUs. It is designed for portable devices, as indicated by its system-shared memory, IGP form factor, and portable-device-dependent display outputs. Its 80 W TDP and lack of power connectors confirm a low-power, integrated design. The recorded benchmark shows it performing within a few percentage points of legacy NVIDIA entry-level parts like the GT 710 and GT 520MX, which suggests it targets basic graphics workloads rather than high-end gaming or compute.

The Intel Data Center GPU Max 1350 is a data center compute accelerator with massive resources: 14336 shading units, 112 ray tracing cores, 96 GB of HBM2e, 2.46 TB/s of memory bandwidth, and 44.44 TFLOPS of FP32 throughput. Its 450 W TDP, OAM Module form factor, and absence of display outputs confirm it is not intended for consumer graphics. The database contains no benchmark scores for it, so its measured performance cannot be quantified. Its 50th percentile ranking is a placeholder based on missing data, not a performance result.

Who should pick which comes down to the platform. The Arc B390 belongs in a portable device where integrated graphics and low power are required. The Data Center GPU Max 1350 belongs in a server or data center environment where compute throughput and memory capacity are paramount. No benchmark data exists to compare them directly, and their specifications are so divergent that any such comparison would be meaningless. The recorded data shows the Arc B390 as a low-tier graphics solution and the Data Center GPU Max 1350 as a high-capacity compute part with no measured graphics performance.

Specification Differences

The two GPUs differ in nearly every specification category recorded in the database.

• Process Node: Arc B390 uses 3 nm; Data Center GPU Max 1350 uses 10 nm.
• Transistors: Arc B390 unknown; Data Center GPU Max 1350 has 100,000 million.
• Die Size: Arc B390 unknown; Data Center GPU Max 1350 is 1280 mm².
• Transistor Density: Arc B390 null; Data Center GPU Max 1350 is 78.1M per mm².
• Base Clock: Arc B390 at 300 MHz; Data Center GPU Max 1350 at 750 MHz.
• Boost Clock: Arc B390 at 2500 MHz; Data Center GPU Max 1350 at 1550 MHz.
• Memory Size: Arc B390 system shared; Data Center GPU Max 1350 has 96 GB.
• Memory Type: Arc B390 system shared; Data Center GPU Max 1350 uses HBM2e.
• Memory Bus Width: Arc B390 system shared; Data Center GPU Max 1350 has 8192 bit.
• Memory Bandwidth: Arc B390 system dependent; Data Center GPU Max 1350 has 2.46 TB/s.
• Shading Units: Arc B390 has 1536; Data Center GPU Max 1350 has 14336.
• TMUs: Arc B390 has 48; Data Center GPU Max 1350 has 896.
• ROPs: Arc B390 has 24; Data Center GPU Max 1350 has 0.
• Ray Tracing Cores: Arc B390 has 12; Data Center GPU Max 1350 has 112.
• Pixel Rate: Arc B390 at 60.00 GPixel/s; Data Center GPU Max 1350 at 0 MPixel/s.
• Texture Rate: Arc B390 at 120.0 GTexel/s; Data Center GPU Max 1350 at 1,388.8 GTexel/s.
• FP32 Performance: Arc B390 at 7.680 TFLOPS; Data Center GPU Max 1350 at 44.44 TFLOPS.
• FP16 Performance: Arc B390 at 15.36 TFLOPS (2:1); Data Center GPU Max 1350 at 44.44 TFLOPS (1:1).
• TDP: Arc B390 at 80 W; Data Center GPU Max 1350 at 450 W.
• Slot Width: Arc B390 is IGP; Data Center GPU Max 1350 is OAM Module.
• Power Connectors: Arc B390 has none; Data Center GPU Max 1350 has null listed.
• Suggested PSU: Arc B390 null; Data Center GPU Max 1350 rated at 850 W.
• Bus Interface: Arc B390 is IGP; Data Center GPU Max 1350 is PCIe 5.0 x16.
• Display Outputs: Arc B390 is portable device dependent; Data Center GPU Max 1350 has no outputs.
• DirectX Support: Arc B390 supports 12 Ultimate (12_2); Data Center GPU Max 1350 supports 12 (12_1).
• Vulkan Support: Arc B390 supports 1.4; Data Center GPU Max 1350 has none listed.
• Release Date: Arc B390 released on 2026-01-26; Data Center GPU Max 1350 released on 2023-01-09.
• Successor: Arc B390 has none; Data Center GPU Max 1350 has H3C Graphics.

FAQ

Q: Does the Intel Arc B390 have a higher boost clock than the Data Center GPU Max 1350?

A: Yes. The Arc B390 boosts to 2500 MHz, while the Data Center GPU Max 1350 boosts to 1550 MHz.

Q: How much memory does the Data Center GPU Max 1350 have?

A: It has 96 GB of HBM2e memory on an 8192-bit bus with 2.46 TB/s of bandwidth.

Q: What is the FP32 performance of the Arc B390?

A: The Arc B390 delivers 7.680 TFLOPS of FP32 performance. The Data Center GPU Max 1350 delivers 44.44 TFLOPS.

Q: Does the Data Center GPU Max 1350 support Vulkan?

A: No. Its Vulkan support is listed as null. It supports DirectX 12 (12_1) and OpenGL 4.6.

Q: What is the benchmark score for the Data Center GPU Max 1350?

A: The database has no recorded benchmark scores for it. Its average benchmark score is 0, and its percentile is 50.

Q: Which GPU has more ray tracing cores?

A: The Data Center GPU Max 1350 has 112 ray tracing cores, while the Arc B390 has 12.

Where Each One Wins

The Arc B390 wins in scenarios requiring integrated graphics with low power consumption. Its 80 W TDP, IGP slot width, and absence of power connectors make it suitable for portable devices where space and thermal limits are tight. It supports a full modern API stack including DirectX 12 Ultimate (12_2) and Vulkan 1.4, which the Data Center GPU Max 1350 does not fully match. Its pixel rate of 60.00 GPixel/s, enabled by its 24 ROPs, gives it actual rasterization capability, unlike the Data Center part which has 0 ROPs and a 0 MPixel/s pixel rate. Its 1482 Steel Nomad score, while low, shows it can outperform several legacy NVIDIA parts by margins of 1.3% to 2.7%. The Arc B390 also carries a 3 nm process node, indicating a much newer manufacturing technology.

The Data Center GPU Max 1350 wins in compute-heavy, memory-intensive data center workloads. Its 14336 shading units and 112 ray tracing cores dwarf the Arc B390's 1536 and 12, respectively. Its FP32 throughput of 44.44 TFLOPS is roughly 5.8 times the Arc B390's 7.680 TFLOPS, and its FP16 rate of 44.44 TFLOPS at a 1:1 ratio exceeds the Arc B390's 15.36 TFLOPS at a 2:1 ratio. Its 96 GB of HBM2e memory with 2.46 TB/s of bandwidth is an order of magnitude beyond the Arc B390's system-shared memory. Its texture rate of 1,388.8 GTexel/s is over 11 times the Arc B390's 120.0 GTexel/s. The Data Center part also has a higher base clock at 750 MHz versus 300 MHz, and its PCIe 5.0 x16 interface provides a dedicated high-bandwidth connection. Its 450 W TDP and 850 W suggested PSU reflect its intended installation in a server or accelerator chassis rather than a portable device. The Data Center GPU Max 1350 also has a successor listed in the database, the H3C Graphics, while the Arc B390 does not.