Intel Unveils Arc Pro B50 and B60 Graphics Cards for Professional Visualization and Artificial Intelligence

Intel has launched its Arc Pro B50 and B60 GPUs, targeting professional graphics workstations and Artificial Intelligence inferencing tasks, at Computex 2025.

Intel announced the debut of its Arc Pro ´Battlemage´ graphics card lineup at Computex 2025, introducing the professional-grade Arc Pro B50 and B60 models. These new cards leverage Intel´s latest Xe2 graphics architecture and are built on the advanced 5 nm BMG-G21 silicon, signaling Intel´s intention to compete at the high end of workstation graphics solutions. The Arc Pro B50 is equipped with 12 GB of memory and is positioned for professional visualization and graphics workstation markets, while the Arc Pro B60 offers a substantial 24 GB of memory, specifically pitched for dual roles in both visualization and Artificial Intelligence inferencing workloads.

Differentiating itself from competitors such as AMD and NVIDIA, Intel opted not to produce reference designs for the Arc Pro B-series. Instead, the company is working closely with a range of board partners to bring custom card designs to market. Notable partners supporting the Arc Pro B-series include ASRock, Gunnir, Maxsun, Sparkle, Onix, Senao, and Lanner, expanding the reach and diversification of these professional GPUs.

The Arc Pro B50 series comes with extensive certifications and validations, offering assurance to users that it performs smoothly with leading content creation applications. In its push to bolster its Artificial Intelligence inferencing capabilities, Intel has introduced the Project Battlematrix Linux software stack and a new workstation platform. These advancements allow deployment of up to eight Arc Pro GPUs in a single system, pooling a total of 192 GB of memory. Such a setup is capable of accelerating machine learning models with over 70 billion parameters, underlining Intel´s ambitions in the high-performance computing and Artificial Intelligence sectors.

74

Impact Score

Artificial Intelligence LLM confessions and geothermal hot spots

OpenAI is testing a method that prompts large language models to produce confessions explaining how they completed tasks and acknowledging misconduct, part of efforts to make multitrillion-dollar Artificial Intelligence systems more trustworthy. Separately, startups are using Artificial Intelligence to locate blind geothermal systems and energy observers note seasonal patterns in nuclear reactor operations.

Saudi Artificial Intelligence startup launches Arabic LLM

Misraj Artificial Intelligence unveiled Kawn, an Arabic large language model, at AWS re:Invent and launched Workforces, a platform for creating and managing Artificial Intelligence agents for enterprises and public institutions.

Contact Us

Got questions? Use the form to contact us.

Contact Form

Clicking next sends a verification code to your email. After verifying, you can enter your message.