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

bigcat12345678

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.

tangjurine

This looks cool

prometheus1992

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

jonesy827

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.

nextaccountic

Is this open weights? Or planned to be

montroser

Hoping this is real. It's too bad to see the signals from Qwen that they will not be releasing a 35B-A3B for the 3.8 lineup. The MoE architecture makes a huge difference for being able to run these local models on reasonable consumer hardware.

jakswa

I'll be comparing the 9B vs Ling 3 Tiny (8B-A1B) as a scout model. Ling tiny is so fast but can be a little too dumb. Hope the 9B strikes a good middleground even if dense/slower.

colingauvin

397 is just too big for two Sparks even at NVFP4. Wish they had made this just a tiny bit smaller.

wyre

This is exciting. Their 9B model benchmarks competitively with Sonnet 4 which is pretty cool to have such a small model compared to one that came out 10 months ago. I’m curious how providers will price their 397B model.

garo-pro

Across five cases it reliably claims to be Claude without being able to name a specific version.

esafak

Apparently this is Jiwei Li's new company. https://ai.miraheze.org/wiki/Ornith https://www.innovatorsunder35.com/the-list/jiwei-li-2020/ I wonder what their angle is going to be; the scene is crowded, and they don't do serving.

htrp

Another day another startup claiming some vague version of RSI to try to close their round.

lsb

The page has comparisons with Qwen 3.6 27b and I’d love to see comparisons with Qwen 3.8 27b, the newer one is much more capable!

hxii

Interestingly, in my own benchmark and testing (in the hopes of finding a good-enough local model to run a personal assistant agent), Ornith-1.0-9B was worse than Qwen3.5-9B which according to their scores should've been reversed. I will definitely pass Ornith-1.5-9B through the gauntlet as well!

rbanffy

It’s time for me to upgrade the main server in my home lab and I’m thinking about which machine should I have. What kind of hardware you’d need to run the 397B one at an acceptable speed?

AIorNot

Can someone parse all that AI generated blather in the post and tell me clearly: 1. Is this self improvement at the model level (updated weights or memory, KV etc) or just by adding agentic code harnesess to guide the output better? Thank you