# DeepX claims inference up to 100B parameters at less than 5 W

- HackerByte page: <https://hackerbyte.net/en/stories/deepx-s-claim-of-performing-inference-for-large-language-models-with-very-low-po-50429545>
- Original source: <https://www.eetimes.com/deepx-tapes-out-second-gen-chip-projects-6-7x-performance-gain-with-lpddr5x-pim/>
- Hacker News discussion: <https://news.ycombinator.com/item?id=50429545>
- Submitted to Hacker News: 2026-11-09T18:33:58.000Z

DeepX's claim of performing inference for large language models with very low power consumption.

## AI-generated summary

No summary is available in this language yet.