Skip to content
AI News HubLIVE
More
Summary only

Skymizer's chip design could embarrass Nvidia and AMD cards

Skymizer unveils HTX301 PCIe AI accelerator using 28nm chips and LPDDR memory, delivering 700B parameter LLM inference at 240W, challenging Nvidia and AMD.

SourceHacker News AIAuthor: anticensor
Skymizer's chip design could embarrass Nvidia and AMD cards
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions

Summary only

Under the source content permission, this page provides an editorial summary, key points, and a link to the original article.

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Skymizer's HTX301 PCIe accelerator runs models up to 700B parameters on a single card at 240W.
  • Uses old 28nm technology and LPDDR memory instead of expensive HBM.
  • Offers up to 384GB memory with efficient compression, outperforming llama.cpp by 9-17.8%.
  • Fits into standard air-cooled servers, enabling on-premises AI without infrastructure upgrades.

Highlights and analysis are generated automatically and may contain errors. Check the original source.

More recent stories on this topic · Models