Skip to content
Live
Trending storyDeveloping

180B Parameters, 32GB of RAM: Pushing MoE Inference to the Limit with Transformers

1 reports1 outlets22 hours agoUpdate

The story so far

No overview yet — start with the coverage timeline below.

Coverage timeline

Follow the coverage to see every side of the story.

18 Nov
  1. Hugging Face Blog
    180B Parameters, 32GB of RAM: Pushing MoE Inference to the Limit with Transformers

    Hugging Face launches 180B parameter MoE model Qwen 3.8, streaming experts directly from SSD via Strata engine, only 6% slower than Strata benchmark in token generation

Heat over time

Now
6
Peak
619 Nov, 01:00
24h change
–

Hover or tap the chart to see each hour; use the arrow keys on a keyboard.