Majestic Labs ditches the GPU to beat Nvidia’s memory wall
Startup Majestic Labs has introduced a server architecture that replaces traditional GPUs with custom AI processing units to solve memory bottlenecks. By using cheaper, high-capacity memory, the company claims to outperform Nvidia hardware in AI inference tasks.
Why it matters
If successful, this approach could significantly lower the cost and power requirements for running large-scale AI models.
The AI hardware conversation is stuck on one word: compute. A startup out of Tel Aviv wants to change the word to memory. Majestic Labs, founded in 2023 by former Google and Meta engineers, has unveiled a server it says can do the work of a rack of Nvidia GPUs. It does so by attacking a different bottleneck.
The pitch, reported by TechRadar , is that pairing pricey GPUs with scarce high-bandwidth memory has become a dead end for AI inference. Running a model is often limited by how much fast memory you can reach, not raw compute. So Majestic ditched the GPU.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in