Intel UHD Graphics 48EU

Intel UHD Graphics 48EU
Intel UHD Graphics 48EU graphics card review

Intel UHD Graphics 48EU: How Memory Affects Performance

Intel UHD Graphics 48EU is a version of the integrated Xe G4 graphics with 48 execution units designed for mobile Tiger Lake processors. Its performance is heavily influenced by memory configuration, power limits, and cooling: the performance difference between laptops in Time Spy exceeds 40%.

In 2026, its performance is sufficient for everyday tasks, video playback, and less demanding gaming. However, it is no longer adequate for modern demanding games.

Where Intel UHD Graphics 48EU is Found

The Xe G4 with 48 EU was installed in entry-level mobile Tiger Lake processors, including the Core i3-1115G4, Core i3-1125G4, Pentium Gold 7505, and Celeron 6305.

Since integrated graphics use the laptop's RAM, the performance of two systems with the same GPU can vary significantly. The results are affected by memory operating mode, GPU frequencies, power limits, and cooling.

Benchmarks Across Different Laptops

In 3DMark, the difference between laptops can reach several percentage points.

Device Processor RAM 3DMark Time Spy Time Spy Graphics
Lenovo ThinkBook 14 G2 ITL Core i3-1115G4 8 GB 715 634
Dell Inspiron 15 5502 Core i3-1115G4 8 GB 804 723
Lenovo IdeaPad 3 15ITL05 Core i3-1115G4 8 GB 888 798
Acer Aspire 5 A515-56-P8NZ Pentium Gold 7505, single-channel RAM 8 GB 718 641
Acer Aspire 5 A515-56-P8NZ Pentium Gold 7505, dual-channel RAM 8 GB 911 822
Realme Book Slim Core i3-1115G4 8 GB 1018 913

The difference is particularly noticeable on the Acer Aspire 5. After switching from single-channel to dual-channel RAM, the Time Spy Graphics score increases from 641 to 822 points, a rise of about 28%.

There are also differences among laptops with the same Core i3-1115G4. The Lenovo ThinkBook 14 G2 scores 634 in Time Spy Graphics, while the Realme Book Slim scores 913. This disparity cannot be explained by memory alone; power limits and cooling also play a significant role.

The average value tells little about the performance of a specific laptop.

Gaming

In Shadow of the Tomb Raider, the Acer Aspire 5 with Pentium Gold 7505 achieves about 25 fps at 1280 x 720 with minimum settings. In Cyberpunk 2077, the Lenovo IdeaPad 3 with Core i3-1115G4 gets around 14-15 fps at 720p with low settings.

Even at 720p, modern demanding games run too slowly.

For older games and less demanding online projects, performance is often sufficient.

Everyday Use and Video

In everyday tasks, high graphical performance is usually not required. The capabilities of the 48EU are enough for the Windows interface, browsing, office applications, and video playback.

Hardware decoding reduces CPU load during video playback, and Intel Quick Sync aids in encoding and transcoding tasks.

For complex video editing and 3D rendering, the 48EU is too slow, but it manages well with video playback and basic editing.

Why RAM is Important

Intel UHD Graphics 48EU has no dedicated video memory, so it utilizes the laptop's RAM.

Single-channel memory limits bandwidth and can significantly reduce graphical performance.

If a laptop is equipped with only one memory module, adding a second can noticeably speed up integrated graphics.

Intel UHD Graphics 48EU in 2026

For browsing, office applications, and video, Intel UHD Graphics 48EU is still adequate.

Older games and less demanding online projects also run at lower graphical settings. However, it is insufficient for modern AAA games, 3D rendering, and other GPU-intensive tasks.

When purchasing a used laptop, it is worthwhile to check the memory configuration, battery condition, screen, and price. In 2026, the 48EU should only be considered as basic graphics in an inexpensive used laptop.

GPU Comparison

Compare UHD Graphics 48EU with other GPUs

Please select GPU from the dropdown list.

Basic

Label Name
Intel
Platform
Integrated
Launch Date
September 2020
Former Codename
Tiger Lake GT2
GPU Lithography
10 nm SuperFin
Model Name
Intel UHD Graphics Xe G4 48EUs
Generation
Tiger Lake
Bus Interface
Ring Bus
RT Cores
No
Compute Units
48
Tensor Cores
?
Tensor Cores are specialized processing units designed specifically for deep learning, providing higher training and inference performance compared to FP32 training. They enable rapid computations in areas such as computer vision, natural language processing, speech recognition, text-to-speech conversion, and personalized recommendations. The two most notable applications of Tensor Cores are DLSS (Deep Learning Super Sampling) and AI Denoiser for noise reduction.
No
TMUs
?
Texture Mapping Units (TMUs) serve as components of the GPU, which are capable of rotating, scaling, and distorting binary images, and then placing them as textures onto any plane of a given 3D model. This process is called texture mapping.
24
Foundry
Intel
Process Size
10 nm SuperFin
Architecture
Xe-LP (Generation 12.1)
Used in CPUs

Memory Specifications

Memory Size
System Shared
Memory Type
System Shared
Memory Bus
?
The memory bus width refers to the number of bits of data that the video memory can transfer within a single clock cycle. The larger the bus width, the greater the amount of data that can be transmitted instantaneously, making it one of the crucial parameters of video memory. The memory bandwidth is calculated as: Memory Bandwidth = Memory Frequency x Memory Bus Width / 8. Therefore, when the memory frequencies are similar, the memory bus width will determine the size of the memory bandwidth.
System Shared
Memory Clock
System Shared
Bandwidth
?
Memory bandwidth refers to the data transfer rate between the graphics chip and the video memory. It is measured in bytes per second, and the formula to calculate it is: memory bandwidth = working frequency × memory bus width / 8 bits.
System Dependent

Display and Media

AV1 Encode/Decode
Decode Only
DisplayPort Extensions
1.4
H.264 Hardware Encode/Decode
Yes
H.265 HEVC Hardware Encode/Decode
Yes
HDMI Version
2.0b
Intel Quick Sync Video
Yes
Max Resolution DP
7680 x 4320 @ 60Hz
Max Resolution eDP
4096 x 2304 @ 60Hz
Max Resolution HDMI
4096 x 2304 @ 60Hz
Number of Displays Supported
4
Outputs
eDP 1.4b, MIPI-DSI 2.0, DP 1.4, HDMI 2.0b

Theoretical Performance

FP32 (float)
?
An important metric for measuring GPU performance is floating-point computing capability. Single-precision floating-point numbers (32-bit) are used for common multimedia and graphics processing tasks, while double-precision floating-point numbers (64-bit) are required for scientific computing that demands a wide numeric range and high accuracy. Half-precision floating-point numbers (16-bit) are used for applications like machine learning, where lower precision is acceptable.
0.8832 TFLOPS

AI Features

AI Software Frameworks Supported by GPU
Intel oneAPI, oneDNN, oneMKL
Intel Deep Learning Boost on GPU
No

Miscellaneous

Shading Units
?
The most fundamental processing unit is the Streaming Processor (SP), where specific instructions and tasks are executed. GPUs perform parallel computing, which means multiple SPs work simultaneously to process tasks.
384
Vulkan Version
?
Vulkan is a cross-platform graphics and compute API by Khronos Group, offering high performance and low CPU overhead. It lets developers control the GPU directly, reduces rendering overhead, and supports multi-threading and multi-core processors.
1.4
OpenCL Version
3.0
OpenGL
4.6
CUDA
No
DirectX
12.1
Power Connectors
None
ROPs
?
The Raster Operations Pipeline (ROPs) is primarily responsible for handling lighting and reflection calculations in games, as well as managing effects like anti-aliasing (AA), high resolution, smoke, and fire. The more demanding the anti-aliasing and lighting effects in a game, the higher the performance requirements for the ROPs; otherwise, it may result in a sharp drop in frame rate.
12

Benchmarks

FP32 (float)
Score
0.8832 TFLOPS
3DMark Time Spy
Score
855
Vulkan
Score
9447
OpenCL
Score
8418

Compared to Other GPU

FP32 (float) / TFLOPS
1.007 +14%
0.988 +11.9%
0.92 +4.2%
0.28 -68.3%
3DMark Time Spy
3817 +346.4%
1205 +40.9%
Vulkan
59828 +533.3%
34688 +267.2%
OpenCL
A2
35144 +317.5%
20836 +147.5%
12393 +47.2%
8849 +5.1%