Intel Arc A350M

Intel Arc A350M

Intel Arc A350M: A Graphics Accelerator for Balancing Work and Play

April 2025


Introduction

Since the release of the first Intel Arc graphics cards in 2022, the company has significantly strengthened its position in the discrete graphics market. The Arc A350M model, aimed at mobile devices and compact PCs, remains relevant in 2025 due to driver updates and optimizations. Let's explore what makes this card noteworthy and who it is suitable for.


Architecture and Key Features

Xe-HPG Architecture: The A350M is built on a hybrid Xe-HPG architecture that combines elements for gaming and professional tasks. The manufacturing process is 6 nm from TSMC, providing a balance between energy efficiency and performance.

Unique Features:

- Ray Tracing: Hardware ray tracing using Xe-core blocks. Despite modest performance (up to 2x speed increase compared to software rendering), driver improvements in 2025 have enhanced stability.

- XeSS (Xe Super Sampling): AI upscaling with support for resolutions up to 4K. In optimized games (such as Cyberpunk 2077: Phantom Liberty), the FPS boost reaches 30-40%.

- FidelityFX Compatibility: Support for AMD technologies, including FSR 3.0, broadening the list of optimized projects.


Memory: Fast but Compact

- Type and Size: GDDR6 4 GB with a 96-bit bus. For 2025, this size is modest, but sufficient for 1080p gaming.

- Bandwidth: 168 GB/s. Allows comfortable handling of textures in medium-weight games, but may experience stutters in 4K due to VRAM limitations.

- Impact on Performance: In Apex Legends (High settings, 1080p), when memory is insufficient, FPS drops by 15-20%, but XeSS compensates for this by reducing workload.


Gaming Performance: Modest but Stable

The card is aimed at 1080p gaming but can also handle 1440p in less demanding projects:

- Cyberpunk 2077 (2025): 45-50 FPS (Medium, XeSS Balanced, ray tracing off). With RT enabled, it drops to 25-30 FPS.

- Fortnite (Chapter 6): 75-80 FPS (Epic, DLSS Performance).

- Hogwarts Legacy 2: 60 FPS (High, 1080p, no RT).

Ray Tracing: Activating RT decreases FPS by 35-50%, but with XeSS/FSR 3.0, gameplay is still reasonable (for example, Control: Ultimate Edition — 40 FPS on Medium RT).


Professional Tasks: More Than Just Gaming

- Video Editing: Rendering acceleration in DaVinci Resolve and Premiere Pro thanks to AV1 and HEVC support. Exporting a 10-minute 4K video takes about 8 minutes.

- 3D Modeling: In Blender (using the Intel oneAPI plugin), rendering a medium complexity scene takes around 12 minutes. For complex tasks, it’s better to choose cards with larger memory.

- Scientific Computing: Support for OpenCL and SYCL, but CUDA is not available. Suitable for training simple neural networks (like TensorFlow with optimizations for Xe-cores).


Power Consumption and Heat Dissipation

- TDP: 35-40 W. Ideal for thin laptops and compact PCs.

- Cooling: Passive and hybrid systems manage without throttling. In gaming laptops (like the ASUS ZenBook Pro 14), temperatures do not exceed 75°C.

- Recommendations: For desktop builds with an external GPU — a case with 2-3 fans and ventilation openings.


Competitor Comparison

- NVIDIA GeForce RTX 3050 Mobile (6 GB): About 15-20% faster in games with DLSS 3.5, but more expensive ($550 compared to $400 for A350M).

- AMD Radeon RX 6500M (4 GB): Comparable in FPS but less effective with ray tracing. Price — $380.

- Intel Arc A370M: The higher-end model with 6 GB GDDR6. Performance gap — 10-15%, price — $450.

Conclusion: The A350M stands out due to its price and support for AV1 but lags in RT scenes.


Practical Tips

- Power Supply: For PCs with an external GPU — at least 400 W (using MSI MAG A400DN as an example).

- Compatibility: Requires PCIe 4.0 x8. Motherboards with Intel 600+ and AMD B550+ chipsets support it without issues.

- Drivers: As of 2025, stability is on par with NVIDIA. It's recommended to update via Intel Driver & Support Assistant.


Pros and Cons

✔️ Pros:

- Price of $400 for new devices.

- Support for AV1 and XeSS.

- Low power consumption.

❌ Cons:

- Only 4 GB of memory.

- Limited performance in 4K.

- RT requires compromises.


Final Conclusion: Who is the Arc A350M Suitable For?

This graphics card is an ideal choice for:

1. Budget Gamers looking to play at 1080p with moderate settings.

2. Content Creators who value AV1 encoding acceleration.

3. Owners of Thin Laptops where silence and longevity are important.

The Intel Arc A350M proves that even three years after its release, effective optimization and a reasonable price can keep a device relevant. If you don't need ultimate 4K gaming but want stability and modern technology — this is a solid option.

Basic

Label Name
Intel
Platform
Mobile
Launch Date
March 2022
Model Name
Arc A350M
Generation
Alchemist
Base Clock
300MHz
Boost Clock
1150MHz
Bus Interface
PCIe 4.0 x8
Transistors
7,200 million
RT Cores
6
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.
48
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.
27.60 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.
55.20 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.
3.533 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.
441.6 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.
1.801 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.
768
L2 Cache
4MB
TDP
25W
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.
24

Benchmarks

FP32 (float)
Score
1.801 TFLOPS
3DMark Time Spy
Score
2758

Compared to Other GPU

FP32 (float) / TFLOPS
1.899 +5.4%
1.854 +2.9%
1.801
1.736 -3.6%
3DMark Time Spy
3953 +43.3%
2758
1770 -35.8%
821 -70.2%