←Story detail

Trending story

English translation is being prepared.

1 reports1 story updatesUpdated Aug 12 23:59

Understand this story

Story summary

The English summary is being updated. See the reporting timeline below.

Latest development · Report

Unsloth compresses Qwen3.8-2.4T-A95B to 397GB and supports local running

Developments

1 confirmed developments

  1. English translation is being prepared.

    Source:Unsloth

Reports and discussion timeline

Browse reports and discussion by time. Their evidence levels remain distinct.

Aug 12

  1. UnslothFirst-partySelected

    Unsloth compresses Qwen3.8-2.4T-A95B to 397GB and supports local running

    Unsloth uses Dynamic 1-bit selective quantization layers to compress Qwen3.8-2.4T-A95B from 4.9TB to 397GB, a 91% reduction in size. The model can now run locally via Unsloth Desktop in more than 410GB of memory or VRAM, and the official team has also released a usage guide and GGUF files.

Related stories

  1. Related storiesEnglish translation is being prepared.
  2. Related storiesEnglish translation is being prepared.
  3. Related storiesMoonshot AI releases flagship model Kimi K3
  4. Related storiesEnglish translation is being prepared.