Intel Arc A370M

Intel Arc A370M

Intel Arc A370M: Detailed Review of the 2025 Mobile GPU

Introduction

Intel's Arc graphics cards have become an important player in the discrete graphics market, offering an alternative to NVIDIA and AMD solutions. In this article, we will explore the mobile version — Intel Arc A370M, which remains popular among budget gaming laptops and workstations even in 2025. We will examine its architecture, performance, energy efficiency, and practical value.


1. Architecture and Key Features

Xe-HPG Architecture

The A370M is built on the Xe-HPG (High-Performance Gaming) microarchitecture, optimized for gaming and professional tasks. The chips are manufactured using a 6nm TSMC process, providing a balance between energy efficiency and performance.

Unique Features

- Ray Tracing (RT): Supports hardware-accelerated ray tracing, although it has fewer RT cores compared to NVIDIA's flagship models.

- XeSS (Xe Super Sampling): Upscaling technology similar to DLSS and FSR. It allows for a 30-50% increase in FPS at 4K without significant loss of detail.

- Compatibility with FidelityFX: Works with open standards from AMD, including FSR 3.0, which expands the list of supported games.


2. Memory: Type, Capacity, and Speed

GDDR6 and Bandwidth

The A370M is equipped with 4 GB of GDDR6 memory and a 128-bit bus. The memory bandwidth reaches 224 GB/s (14 Gbps × 128 bits / 8). This is sufficient for most games at 1080p, but in 2025, 4 GB may become a bottleneck for projects with ultra textures or when working with professional applications.

Impact on Performance

- In Cyberpunk 2077 (1080p, Ultra), memory usage rarely exceeds 3.5 GB, but in Horizon Forbidden West (1440p, RT On), stuttering may occur due to VRAM limitations.

- For 4K video editing in DaVinci Resolve, 4 GB is the minimum threshold.


3. Gaming Performance

Average FPS in Popular Games (1080p)

- Fortnite (Epic, XeSS Quality): 75-90 FPS.

- Call of Duty: Modern Warfare V (Ultra, RT Off): 60-70 FPS.

- Cyberpunk 2077 (High, RT Medium + XeSS Balanced): 45-55 FPS.

Resolution Support

- 1080p: Ideal choice for the A370M.

- 1440p: Requires reducing settings to Medium or using XeSS/FSR.

- 4K: Only feasible in less demanding games (e.g., CS2, Dota 2).

Ray Tracing

Enabling RT reduces FPS by 25-40%, but losses are compensated with XeSS. For instance, in Minecraft RTX, the card provides a stable 30 FPS at XeSS Performance.


4. Professional Tasks

Video Editing and Rendering

- Premiere Pro: Rendering acceleration thanks to Intel Quick Sync support. Exporting a 10-minute 4K video takes ~8 minutes.

- Blender: In the BMW CPU + GPU test, rendering completes in 14 minutes (compared to 9 minutes with the RTX 3050).

Scientific Calculations

- Supports OpenCL and oneAPI, but CUDA-optimized tasks (e.g., in MATLAB) run slower than on NVIDIA.


5. Power Consumption and Heat Dissipation

TDP and Cooling Recommendations

- The A370M has a TDP of 50-75 W, making it suitable for slim laptops.

- In gaming scenarios, temperatures reach 75-85°C, so an effective cooling system with 2-3 heat pipes is essential.

Case Selection Tips

For laptops with the A370M, models with rear ventilation holes and adjustable performance modes (e.g., ASUS TUF Dash F15) are preferred.


6. Comparison with Competitors

NVIDIA RTX 3050 Mobile

- NVIDIA Advantages: Better driver optimization, DLSS 3.5, higher FPS in RT scenes.

- Intel Advantages: Lower price (~$300 vs. $400), AV1 encoding support.

AMD Radeon RX 6600M

- AMD Advantages: 8 GB VRAM, better performance at 1440p.

- Intel Advantages: Energy efficiency, XeSS.


7. Practical Tips

Power Supply

A 120-150 W adapter is sufficient for a laptop with the A370M. However, when simultaneously stressing both the CPU and GPU (e.g., while streaming), it's better to have a power reserve.

Compatibility

- Platforms: Works best in tandem with Intel's 12th-generation processors and newer (optimization through Deep Link).

- Drivers: By 2025, stability has improved, but artifacts may still occur in older games (pre-2022).


8. Pros and Cons

Pros

- Affordable price ($300-400 for laptops).

- Support for modern technologies: RT, XeSS, AV1.

- Low power consumption.

Cons

- Only 4 GB VRAM.

- Limited performance at 4K.

- Drivers still lag behind NVIDIA in optimization.


9. Final Conclusion: Who Should Get the A370M?

This graphics card is an excellent choice for:

- Budget gamers looking to play at 1080p with high settings.

- Students and professionals needing a laptop for video editing and 3D modeling without overspending.

- Technology enthusiasts wanting to try an alternative to NVIDIA/AMD.

Conclusion: The Intel Arc A370M proves that even in 2025, one can achieve a respectable gaming experience and work capabilities without purchasing top-tier GPUs. The key is to consider its limitations and leverage strengths like XeSS and energy efficiency.

Basic

Label Name
Intel
Platform
Mobile
Launch Date
March 2022
Model Name
Arc A370M
Generation
Alchemist
Base Clock
300MHz
Boost Clock
1550MHz
Bus Interface
PCIe 4.0 x8
Transistors
7,200 million
RT Cores
8
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.
64
Foundry
TSMC
Process Size
6 nm
Architecture
Generation 12.7

Memory Specifications

Memory Size
4GB
Memory Type
GDDR6
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.
64bit
Memory Clock
1750MHz
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.
112.0 GB/s

Theoretical Performance

Pixel Rate
?
Pixel fill rate refers to the number of pixels a graphics processing unit (GPU) can render per second, measured in MPixels/s (million pixels per second) or GPixels/s (billion pixels per second). It is the most commonly used metric to evaluate the pixel processing performance of a graphics card.
49.60 GPixel/s
Texture Rate
?
Texture fill rate refers to the number of texture map elements (texels) that a GPU can map to pixels in a single second.
99.20 GTexel/s
FP16 (half)
?
An important metric for measuring GPU performance is floating-point computing capability. Half-precision floating-point numbers (16-bit) are used for applications like machine learning, where lower precision is acceptable. 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.
6.349 TFLOPS
FP64 (double)
?
An important metric for measuring GPU performance is floating-point computing capability. Double-precision floating-point numbers (64-bit) are required for scientific computing that demands a wide numeric range and high accuracy, while single-precision floating-point numbers (32-bit) are used for common multimedia and graphics processing tasks. Half-precision floating-point numbers (16-bit) are used for applications like machine learning, where lower precision is acceptable.
793.6 GFLOPS
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.
3.237 TFLOPS

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.
1024
L2 Cache
4MB
TDP
35W
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.
1.3
OpenCL Version
3.0
OpenGL
4.6
DirectX
12 Ultimate (12_2)
Shader Model
6.6
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.
32

Benchmarks

FP32 (float)
Score
3.237 TFLOPS
3DMark Time Spy
Score
3489
Blender
Score
380.77

Compared to Other GPU

FP32 (float) / TFLOPS
3.384 +4.5%
3.237
3.092 -4.5%
2.989 -7.7%
3DMark Time Spy
6327 +81.3%
4606 +32%
3489
2236 -35.9%
1338 -61.7%
Blender
1506.77 +295.7%
848 +122.7%
380.77
45.58 -88%