Ornith-1.5: From Self-Scaffolding to Self-Improvement

5 comments

• jonesy827 0 minutes ago
  I've been using the 35B-A3B today for some web scraping work, and it has been on par with Qwen3.8 27B at a much higher speed and at a higher quant (q4 vs q8). I'm impressed.
• prometheus1992 13 minutes ago
  Can't wait to try this. Ornith1 (9B) was a really nice model. I have been running it locally using - https://github.com/deepanwadhwa/samosa-chat
• bigcat12345678 48 minutes ago
  How is ornith-1.5's base model developed? Is the base model one of the Open weights models, or one pre trained by ornith team from scratch? I couldn't find information to answer this question in the article.
  [-]
  • goldemerald 44 minutes ago
    It looks like they post-trained Qwen3.6. Interesting to see how far they could improve it with they harness/algorithm.
• tangjurine 20 minutes ago
  This looks cool