ASUS unveils quad-fan GeForce RTX 5090 ROG MATRIX GPU

ASUS has showcased a 30th anniversary special edition GeForce RTX 5090 ROG MATRIX GPU with an air-cooled quad-fan push-pull design and a high-power delivery option that raises total board power to 800 watts.

ASUS officially revealed its 30th anniversary special edition GeForce RTX 5090 ROG MATRIX GPU, confirming an air-cooled design that uses four large fans in a push-pull configuration. The layout mirrors elements of ASUS´s RTX 5090 Astral model, with three fans at the front and one at the back. The GPU shroud is finished in a prominent ROG red and includes a distinct ring on one fan carrying an acrylic plate with the ROG MATRIX logo.

The company offers an option for BTF-supplied power delivery along with a 16-pin 12V-2×6 connector that permits a total power setting of up to 800 watts, well above the 575 watts of the Founders Edition GPU. ASUS states that this power capability provides a 10% performance uplift on its own. The boost clock frequency is confirmed at 2,730 MHz. To support the increased thermal and electrical demands, ASUS uses 3 oz copper PCB layers to improve heat dissipation and reduce voltage drop across components. For die-to-heatsink contact, the card uses liquid metal to maximize heat transfer, which ASUS says is necessary given the card´s potential to consume 800 watts.

ASUS has not announced pricing or final specifications such as memory clock, though the article notes an expectation that the ROG MATRIX will be overclocked out of the box. The card has not yet been evaluated in professional overclocking labs, and ASUS will sell only 1,000 units, raising questions about whether anyone will attempt extreme overclocking records on this limited edition. Additional details and final specs remain not stated by ASUS at this time.

65

Impact Score

European Commission clarifies high-risk Artificial Intelligence rules

The European Commission’s draft guidance maps how high-risk Artificial Intelligence classifications may apply to agentic systems, regulated products, biometrics, employment tools, and financial services. The guidance signals narrow exceptions and a broad view of systems that materially influence regulated decisions.

NVIDIA confidential computing expands Apple private cloud compute

NVIDIA GPUs with Confidential Computing will support confidential inference for Apple’s Private Cloud Compute as it expands to Google Cloud. The collaboration brings NVIDIA Blackwell GPUs into the hardware security architecture behind some next-generation Apple Intelligence features.

Five themes shaping Artificial Intelligence in 2026

Midway through 2026, generative Artificial Intelligence is becoming routine at work while raising sharper concerns about abuse, conflict, backlash, and scientific reliability. The field looks powerful but unsettled, with its long-term impact still unclear.

Longevity drugs and Artificial Intelligence trends

David Sinclair is preparing human tests of a reprogramming drug aimed at whole-body rejuvenation. A broader technology roundup tracks major Artificial Intelligence developments, policy fights, chip restrictions, and emerging biotechnology.

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.