Thread

1. danbrooks · 1789684929 · focus · HN ↗

   Nice! Does anyone know how this compares to the Unsloth quantizations of this model? <a href="https:&#x2F;&#x2F;unsloth.ai&#x2F;docs&#x2F;models&#x2F;qwen3.8#run-qwen3.8-guide">https:&#x2F;&#x2F;unsloth.ai&#x2F;docs&#x2F;models&#x2F;qwen3.8#run-qwen3.8-guide

   1. 0xbadcafebee · 1789689422 · focus · HN ↗

      Came to ask the same. From my really rough understanding, it seems like Unsloth&#x27;s method allows a slightly higher precision at a higher file size, while PrismML&#x27;s uses a different approach to achieve a smaller size (and presumably less precision).

Unofficial Hacker News client; not affiliated with Y Combinator.