Saturday, 20 Sep 2025
  • Contact
  • Privacy Policy
  • Terms & Conditions
  • DMCA
logo logo
  • World
  • Politics
  • Crime
  • Economy
  • Tech & Science
  • Sports
  • Entertainment
  • More
    • Education
    • Celebrities
    • Culture and Arts
    • Environment
    • Health and Wellness
    • Lifestyle
  • 🔥
  • Trump
  • House
  • VIDEO
  • White
  • ScienceAlert
  • Trumps
  • Watch
  • man
  • Health
  • Season
Font ResizerAa
American FocusAmerican Focus
Search
  • World
  • Politics
  • Crime
  • Economy
  • Tech & Science
  • Sports
  • Entertainment
  • More
    • Education
    • Celebrities
    • Culture and Arts
    • Environment
    • Health and Wellness
    • Lifestyle
Follow US
© 2024 americanfocus.online – All Rights Reserved.
American Focus > Blog > Tech and Science > DeepSeek-V3 now runs at 20 tokens per second on Mac Studio, and that’s a nightmare for OpenAI
Tech and Science

DeepSeek-V3 now runs at 20 tokens per second on Mac Studio, and that’s a nightmare for OpenAI

Last updated: March 24, 2025 1:16 pm
Share
DeepSeek-V3 now runs at 20 tokens per second on Mac Studio, and that’s a nightmare for OpenAI
SHARE

DeepSeek, a Chinese AI startup, has recently unveiled its latest large language model, DeepSeek-V3-0324, which has already garnered attention in the AI industry for its capabilities and unique deployment strategy. The 641-gigabyte model is freely available for commercial use under an MIT license and has the ability to run on consumer-grade hardware, such as Apple’s Mac Studio with the M3 Ultra chip.

The launch of DeepSeek-V3-0324 was a quiet one, with no whitepaper, blog post, or marketing push accompanying its release. This stealth approach is in stark contrast to the typical hype surrounding product launches by Western AI companies. Early reports suggest significant improvements over the previous version, with testers praising the model’s performance metrics.

The model’s architecture, based on a mixture-of-experts (MoE) approach, activates only a fraction of its parameters during specific tasks, leading to improved efficiency. Additional technologies like Multi-Head Latent Attention (MLA) and Multi-Token Prediction (MTP) further enhance the model’s speed and performance. Notably, a 4-bit quantized version reduces the storage footprint, making it feasible to run on consumer hardware like the Mac Studio.

DeepSeek’s open-source approach challenges the closed garden model of Silicon Valley companies, emphasizing the importance of freely available AI technology to drive innovation. This strategy has accelerated China’s AI capabilities, with other tech giants like Baidu, Alibaba, and Tencent following suit in open-sourcing their models.

The release of DeepSeek-V3-0324 sets the stage for the upcoming DeepSeek-R2 model, expected to focus on reasoning capabilities. This open-source reasoning model could democratize access to advanced AI systems that are currently limited to well-funded organizations. The model’s technical precision and formal communication style reflect a deliberate design choice for professional and technical applications.

See also  World's first baby born by IVF done almost entirely by a machine

Overall, DeepSeek’s open-source strategy is reshaping the global AI landscape, narrowing the gap between China and the US in AI capabilities. By making advanced AI technology freely available, DeepSeek is enabling exponential innovation and potentially influencing how AI reshapes our world.

TAGGED:DeepSeekV3MacnightmareOpenAIrunsStudiotokens
Share This Article
Twitter Email Copy Link Print
Previous Article Avoidable deaths are on the rise in the United States, yet falling in many peer nations Avoidable deaths are on the rise in the United States, yet falling in many peer nations
Next Article 114 Meaningful Report Card Comments That Caregivers & Students Will Value 114 Meaningful Report Card Comments That Caregivers & Students Will Value
Leave a comment

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

Popular Posts

UCS Expert Testifies on the New Clean Electricity Tax Credits

The recent public hearing hosted by the US Department of the Treasury and the Internal…

August 28, 2024

Warren Buffett keeps winning. These 4 charts show how.

Warren Buffett's investment strategies continue to prove successful, even in the face of market volatility.…

May 3, 2025

Maple Leafs should not hesitate to dress Ryan Reaves in Game 2 after Panthers’ playstyle in series opener

The Toronto Maple Leafs are facing a tough challenge in their series against the Florida…

May 5, 2025

How the World Series played a role in NFL and Roc Nation’s Super Bowl partnership

Jay-Z's selection of Kendrick Lamar to headline the Super Bowl LIX halftime show in February…

November 2, 2024

Making the Holidays More Sustainable

The holiday season is often a time of joy and celebration, but it can also…

December 10, 2024

You Might Also Like

Why are so many young people getting cancer?
Tech and Science

Why are so many young people getting cancer?

September 20, 2025
Peacemaker Season 2: Earth-X Theory Explained
Tech and Science

Peacemaker Season 2: Earth-X Theory Explained

September 20, 2025
Great White Sharks Were Scared From Their Habitat by Just Two Predators : ScienceAlert
Tech and Science

Great White Sharks Were Scared From Their Habitat by Just Two Predators : ScienceAlert

September 20, 2025
4 Ways The Google Pixel Phone Home Screen Could Be Improved
Tech and Science

4 Ways The Google Pixel Phone Home Screen Could Be Improved

September 20, 2025
logo logo
Facebook Twitter Youtube

About US


Explore global affairs, political insights, and linguistic origins. Stay informed with our comprehensive coverage of world news, politics, and Lifestyle.

Top Categories
  • Crime
  • Environment
  • Sports
  • Tech and Science
Usefull Links
  • Contact
  • Privacy Policy
  • Terms & Conditions
  • DMCA

© 2024 americanfocus.online –  All Rights Reserved.

Welcome Back!

Sign in to your account

Lost your password?