← All stories
● Covered by 1 source · 1 reportMedium impact1 neutral

DEEPX Demonstrates AI Chip Running 40 Degrees Cooler Than Competitors

🔄 Updated 10h ago
New to BrevFeed? We gather this story from every outlet covering it into one summary — ranked by real-world impact, not just the latest headline — so you never miss what matters. What is BrevFeed? →

Key points

  • DEEPX DX-M1 AI chip runs significantly cooler than competitors.
  • Demonstrated 25-40°C temperature difference under AI workload.
  • Aims to reduce heat, power, and cooling needs in AI data centers.
  • DX-M1 produced on Samsung 5nm, DX-M2 planned for Samsung 2nm.

Cooler AI Chips for Data Centers

DEEPX, a South Korean chip startup, has demonstrated its DX-M1 AI processor, highlighting its thermal efficiency. The company claims its chip operates 25 to 40 degrees Celsius cooler than competing AI chips when processing the same AI workload. This development is significant given the increasing concerns over heat generation, power consumption, and cooling requirements in modern AI data centers.

Thermal Demonstration and Claims

The DX-M1's cool-running capabilities were illustrated in a demonstration where a knob of butter remained solid on the DEEPX chip, while it melted on rival chips. DEEPX CEO Kim Nok-won stated that every competitor chip melted the butter except the DX-M1. While the demonstration visually conveyed the temperature difference, specific details regarding the speed at which each processor completed the test workload were not provided.

Addressing Data Center Challenges

The proliferation of AI data centers globally is raising concerns about their environmental and economic impact, largely due to the extensive power and cooling infrastructure required for hot-running processors. DEEPX's approach focuses on making the AI chips themselves run cooler, which could lead to reduced operational costs and a smaller environmental footprint for AI computing facilities.

Production and Future Plans

The DX-M1 NPU has been in production on Samsung's 5nm process since August 2025 and has secured approximately $13.3 million in orders. DEEPX plans to develop the next-generation DX-M2 AI chip, which will be based on Samsung's 2nm process, with mass production targeted for the second half of 2027. These NPUs are intended for edge computing and robotics applications.

✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →

The daily brief

One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.

One email a day. Unsubscribe in one click, any time.

Today's brief

Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.

~4 min · 3 stories · Nov 09

▶ Play today's brief Listen on Spotify

New every morning, and the back catalogue is archived by date.

Reporting from

South Korean startup DEEPX showcased its DX-M1 AI chip, which reportedly runs 25 to 40 degrees Celsius cooler than rival chips under the same AI workload. This thermal efficiency could address significant heat, power, and cooling challenges in AI data centers, potentially reducing infrastructure costs and environmental impact.