Intel Data Center GPU Flex 140
Intel graphics card specifications and benchmark scores
Ray TracingAt a Glance
IntelIntel Data Center GPU Flex 140 Specifications
GPU Core
Shader units and compute resources
The Intel Data Center GPU Flex 140 GPU core specifications define its raw processing power for graphics and compute workloads. Shading units (also called CUDA cores, stream processors, or execution units depending on manufacturer) handle the parallel calculations required for rendering. TMUs (Texture Mapping Units) process texture data, while ROPs (Render Output Units) handle final pixel output. Higher shader counts generally translate to better GPU benchmark performance, especially in demanding games and 3D applications.
Data Center GPU Flex 140 Clock Speeds
GPU and memory frequencies
Clock speeds directly impact the Data Center GPU Flex 140's performance in GPU benchmarks and real-world gaming. The base clock represents the minimum guaranteed frequency, while the boost clock indicates peak performance under optimal thermal conditions. Memory clock speed affects texture loading and frame buffer operations. The Data Center GPU Flex 140 by Intel dynamically adjusts frequencies based on workload, temperature, and power limits to maximize performance while maintaining stability.
Intel's Data Center GPU Flex 140 Memory
VRAM capacity and bandwidth
VRAM (Video RAM) is dedicated memory for storing textures, frame buffers, and shader data. The Data Center GPU Flex 140's memory capacity determines how well it handles high-resolution textures and multiple displays. Memory bandwidth, measured in GB/s, affects how quickly data moves between the GPU and VRAM. Higher bandwidth improves performance in memory-intensive scenarios like 4K gaming. The memory bus width and type (GDDR6, GDDR6X, HBM) significantly influence overall GPU benchmark scores.
Data Center GPU Flex 140 by Intel Cache
On-chip cache hierarchy
On-chip cache provides ultra-fast data access for the Data Center GPU Flex 140, reducing the need to fetch data from slower VRAM. L1 and L2 caches store frequently accessed data close to the compute units. AMD's Infinity Cache (L3) dramatically increases effective bandwidth, improving GPU benchmark performance without requiring wider memory buses. Larger cache sizes help maintain high frame rates in memory-bound scenarios and reduce power consumption by minimizing VRAM accesses.
Data Center GPU Flex 140 Theoretical Performance
Compute and fill rates
Theoretical performance metrics provide a baseline for comparing the Intel Data Center GPU Flex 140 against other graphics cards. FP32 (single-precision) performance, measured in TFLOPS, indicates compute capability for gaming and general GPU workloads. FP64 (double-precision) matters for scientific computing. Pixel and texture fill rates determine how quickly the GPU can render complex scenes. While real-world GPU benchmark results depend on many factors, these specifications help predict relative performance levels.
Data Center GPU Flex 140 Ray Tracing & AI
Hardware acceleration features
The Intel Data Center GPU Flex 140 includes dedicated hardware for ray tracing and AI acceleration. RT cores handle real-time ray tracing calculations for realistic lighting, reflections, and shadows in supported games. Tensor cores (NVIDIA) or XMX cores (Intel) accelerate AI workloads including DLSS, FSR, and XeSS upscaling technologies. These features enable higher visual quality without proportional performance costs, making the Data Center GPU Flex 140 capable of delivering both stunning graphics and smooth frame rates in modern titles.
Xe-HPG Architecture & Process
Manufacturing and design details
The Intel Data Center GPU Flex 140 is built on Intel's Xe-HPG architecture, which defines how the GPU processes graphics and compute workloads. The manufacturing process node affects power efficiency, thermal characteristics, and maximum clock speeds. Smaller process nodes pack more transistors into the same die area, enabling higher performance per watt. Understanding the architecture helps predict how the Data Center GPU Flex 140 will perform in GPU benchmarks compared to previous generations.
Power & Thermal
TDP and power requirements
Power specifications for the Intel Data Center GPU Flex 140 determine PSU requirements and thermal management needs. TDP (Thermal Design Power) indicates the heat output under typical loads, guiding cooler selection. Power connector requirements ensure adequate power delivery for stable operation during demanding GPU benchmarks. The suggested PSU wattage accounts for the entire system, not just the graphics card. Efficient power delivery enables the Data Center GPU Flex 140 to maintain boost clocks without throttling.
Data Center GPU Flex 140 by Intel Physical & Connectivity
Dimensions and outputs
Physical dimensions of the Intel Data Center GPU Flex 140 are critical for case compatibility. Card length, height, and slot width determine whether it fits in your chassis. The PCIe interface version affects bandwidth for communication with the CPU. Display outputs define monitor connectivity options, with modern cards supporting multiple high-resolution displays simultaneously. Verify these specifications against your case and motherboard before purchasing to ensure a proper fit.
Intel API Support
Graphics and compute APIs
API support determines which games and applications can fully utilize the Intel Data Center GPU Flex 140. DirectX 12 Ultimate enables advanced features like ray tracing and variable rate shading. Vulkan provides cross-platform graphics capabilities with low-level hardware access. OpenGL remains important for professional applications and older games. CUDA (NVIDIA) and OpenCL enable GPU compute for video editing, 3D rendering, and scientific applications. Higher API versions unlock newer graphical features in GPU benchmarks and games.
Data Center GPU Flex 140 Product Information
Release and pricing details
The Intel Data Center GPU Flex 140 is manufactured by Intel as part of their graphics card lineup. Release date and launch pricing provide context for comparing GPU benchmark results with competing products from the same era. Understanding the product lifecycle helps evaluate whether the Data Center GPU Flex 140 by Intel represents good value at current market prices. Predecessor and successor information aids in tracking generational improvements and planning future upgrades.
About Intel Data Center GPU Flex 140
Power and Cooling
The Intel Data Center GPU Flex 140 is a remarkably power-efficient accelerator, drawing just 75 W of total board power. This low TDP places it in the same thermal envelope as a typical entry-level desktop processor, which has profound implications for system design. The recommended power supply is a modest 250 W unit, meaning this card can be dropped into pre-existing servers or workstations with minimal power delivery upgrades. A single 8-pin PCIe power connector is required, and the card occupies a single slot, making it physically compact for dense data center deployments where space is at a premium. The 170 mm length and 70 mm height further underscore its small footprint, allowing for high-density configurations in chassis that would reject larger accelerators.
The 75 W TDP is not just a number; it dictates cooling strategy. Because the power draw is so low, a simple passive or low-profile active heatsink suffices. The single-slot design ensures that adjacent PCIe slots remain unobstructed, which is critical in multi-GPU servers. The thermal solution does not need to move large volumes of air, so acoustic noise and airflow impedance are minimized. This makes the Flex 140 suitable for environments where dense compute is required but where power budgets and physical space are constrained. The 6 nm process node from TSMC, with 7,200 million transistors on a 157 mm² die, is the enabling factor—the high transistor density (45.9 million per mm²) allows for substantial compute capability within a power envelope that would traditionally be associated with lesser hardware.
Ray Tracing and Feature Set
The Flex 140 includes dedicated ray tracing hardware in the form of 8 RT cores, built on the Xe-HPG architecture. This is a data center part that does not skimp on graphics features. The API support is comprehensive: DirectX 12 Ultimate (12_2), Vulkan 1.4, and OpenGL 4.6. The DirectX 12 Ultimate designation confirms support for hardware-accelerated ray tracing, mesh shaders, and variable rate shading—features that are typically associated with consumer gaming GPUs but are increasingly relevant for professional visualization and cloud gaming workloads.
The presence of RT cores means that ray-traced workloads, whether for architectural visualization, film rendering, or cloud-based interactive ray tracing, will have dedicated hardware acceleration. The FP32 throughput is 3.994 TFLOPS, with FP16 reaching 7.987 TFLOPS via the 2:1 ratio. This dual-rate FP16 capability is significant for AI inference and certain scientific workloads, though the card does not list a separate tensor core count. The pixel rate of 62.40 GPixel/s and texture rate of 124.8 GTexel/s indicate that the rasterization pipeline is well-balanced for its class. Display output includes 1x HDMI 2.1 and 3x DisplayPort 2.0, which is a strong feature set for a data center card that may also drive direct-attached displays in remote workstation scenarios.
Memory Subsystem
The memory configuration is one of the most distinctive aspects of the Flex 140. It ships with 6 GB of GDDR6 memory on a 96-bit bus, yielding a bandwidth of 186.0 GB/s. The memory clock runs at 1937 MHz, translating to an effective data rate of 15.5 Gbps. This is a deliberately balanced configuration: the bus width is narrow, but the high effective clock partially compensates.
For high-resolution workloads, the 6 GB capacity is the primary constraint, not bandwidth. At 4K resolutions, frame buffers for complex scenes can easily exceed 6 GB, particularly with ray tracing enabled and high-quality textures. The 186.0 GB/s bandwidth, while adequate for 1080p and moderate 1440p workloads, will become a limiting factor when processing large, high-resolution datasets or when multiple virtual machines access the GPU simultaneously. The 96-bit bus is a clear indicator that this is not a high-end compute part; it is optimized for density and efficiency rather than raw memory throughput. In scenarios where the working set fits within 6 GB, the bandwidth is sufficient to keep the 1024 shading units fed. The 32 ROPs and 64 TMUs are commensurate with this memory subsystem, ensuring that pixel throughput does not outstrip memory access capabilities.
How It Compares
The FACT PACK lists no nearest rivals for the Flex 140, and its benchmark score is zero with a 50th percentile ranking among all GPUs. The absence of comparative data means that position must be inferred from architectural characteristics. Within the Intel data center lineup, this card succeeds the H3C Graphics, indicating it is part of a broader family of Xe-HPG accelerators designed for cloud gaming and media processing. The 50th percentile placement suggests it sits at the median of all GPUs ever benchmarked, which is a credible position for a low-power, single-slot card that prioritizes density over absolute performance.
Compared to typical data center accelerators that emphasize FP32 or tensor throughput, the Flex 140's 3.994 TFLOPS is clearly oriented toward graphics and video workloads rather than heavy compute. Its 75 W TDP is dramatically lower than most server GPUs, which often exceed 200 W. This means that a single server chassis can host many more Flex 140 cards than competing solutions, multiplying the total throughput for parallel, low-intensity tasks. The 8 RT cores provide a feature that many older data center cards lack entirely, making it a forward-looking choice for ray-traced rendering in the cloud. The PCIe 4.0 x8 interface is sufficient for the card's bandwidth needs, though it does limit data transfer rates compared to x16 implementations.
Who Should Consider It
The Flex 140 is for organizations that need to deploy many GPU instances in a single server without tripping power breakers or exceeding thermal limits. The 75 W TDP and 250 W PSU recommendation make it feasible to integrate in chassis that were never designed for high-power accelerators. For cloud gaming providers, the 6 GB VRAM is adequate for 1080p and light 1440p gaming sessions, and the RT cores enable ray-traced effects that are increasingly expected in modern titles. DirectX 12 Ultimate support ensures compatibility with the latest game engines.
For media streaming and transcoding workloads, the low power draw allows for 24/7 operation with minimal operational cost. The card's small physical size (170 mm length, single-slot) fits into 1U servers where full-length, dual-slot cards cannot. The 50th percentile performance ranking indicates that it is not a speed demon; users should not expect class-leading frame rates. Instead, the value is in the form factor and efficiency. Organizations running virtual desktop infrastructure (VDI) will find the 3.994 TFLOPS sufficient for productivity applications and casual gaming. The 3x DisplayPort 2.0 outputs are unusual for a data center card and suggest it can also serve as a direct-attached workstation accelerator.
FAQ
Q: What is the maximum power draw of this card?
A: The TDP is 75 W, and the recommended power supply is 250 W.
Q: Does it support hardware ray tracing?
A: Yes, it includes 8 dedicated RT cores and supports DirectX 12 Ultimate (12_2).
Q: How much memory does it have and what type?
A: It has 6 GB of GDDR6 memory on a 96-bit bus, providing 186.0 GB/s of bandwidth.
Q: What is the production status?
A: The card is end-of-life, with the successor being the H3C Graphics.
Q: What display outputs are available?
A: It offers 1x HDMI 2.1 and 3x DisplayPort 2.0 outputs.
Q: What is the physical size?
A: It measures 170 mm in length, 70 mm in height, and 29 mm in width, and is a single-slot card.
Benchmark Performance
The Flex 140 has a benchmark score of zero in the database, with a percentile rank of 50 among all GPUs. This zero score is a placeholder, but the 50th percentile positioning provides a meaningful anchor. Half of all GPUs are slower, and half are faster. In absolute terms, the 3.994 TFLOPS FP32 performance is the key compute metric. This places it in the lower-mid range of modern GPUs, but the context is crucial: this is a 75 W, single-slot card. A typical high-end consumer GPU at 300 W+ will deliver five to ten times the FP32 throughput, but it will also require significantly more power and physical space.
The FP16 performance of 7.987 TFLOPS (2:1 ratio) is double the FP32 rate, which is a standard configuration for Xe-HPG architecture. This is beneficial for AI inference tasks that use FP16 precision, effectively doubling the compute throughput for those workloads. The texture rate of 124.8 GTexel/s and pixel rate of 62.40 GPixel/s are consistent with the 64 TMUs and 32 ROPs. In practical gaming terms, this translates to solid 1080p performance in most titles and playable 1440p in less demanding games. The 186.0 GB/s bandwidth will be the bottleneck at higher resolutions, particularly with high-resolution texture packs. The 8 RT cores provide ray tracing capability, but the overall compute power is limited, so ray-traced workloads will need to be scaled back in resolution or complexity. The 50th percentile ranking means that users should expect performance that is "middle of the road"—not embarrassing, but not impressive either. For the target use case of dense, low-power deployment, this is an entirely acceptable trade-off. The card is not designed to win benchmark crown; it is designed to win density and efficiency awards. In that context, the 75 W TDP and single-slot form factor are the real headline numbers, and the compute performance is sufficient for the intended workloads.
Detailed benchmark scores and charts for the Intel Data Center GPU Flex 140 are below.
Benchmark Scores
No benchmark data available for this GPU.
Compare with Other GPUs
Select another GPU to compare specifications and benchmarks side-by-side.
Browse GPUs