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

110

CCommonGuy about 4 hours ago 27 commentsRead Article on ornith.ai

ZH version is available. Content is displayed in original English for accuracy.

⚡ Community Insights

Discussion Sentiment

80% Positive

Analyzed from 637 words in the discussion.

Discussion (27 Comments)Read Original on HackerNews

montroser•about 2 hours ago

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.

dofm•14 minutes ago

Quick tests suggest it’s pretty good at reasoning and tool use (keen to search to check its thinking) and it seems to waste much less time thinking, too.

So it feels very fast.

But it does not seem to be better than Qwen 3.6 35B at coding. A bit worse, I think, though I will test it more.

If you have a machine that can fit a 35B model in VRAM, I would suggest testing Muse Glimmer with (from memory)

  Reasoning strength: low

in the system prompt.

Despite being a dense model, this is actually capable of solving code problems faster than the Qwen MoE, despite having only one fifth of the raw token performance.

parsimo2010•about 1 hour ago

Honest question/suggestion for the HN audience- Since Qwen released the weights for Qwen3.8 2.4T-A95B and we already have the staring point of Qwen3.6 35B-A3B, couldn't someone distill the bigger model and make a "pseudo" Qwen3.8 35B-A3B? Sure, it wouldn't be an official Qwen release but couldn't someone improve on Qwen 3.6 and get the thing everyone is asking for?

I am calling this a suggestion for the audience because I don't have the will/resources to do this.

WASDx•16 minutes ago

"Qwen3.8 35B-A3B" and 4B/9B variants are already on huggingface distilled by hobbyists.

mirekrusin•32 minutes ago

Personally I find speculative decoding much better strategy than MoE – performance wise it's there at 90-100 t/s on 2x4090, great intelligence – really great fit.

d4rkp4ttern•27 minutes ago

A lot of people, including me, don’t want to bother with GPUs, they’d rather run it on their M1-M5 MacBook. For example the 35B-A3B is very usable even on a M1 64GB MacBook.

jonesy827•about 2 hours 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.

jakswa•about 1 hour ago

I had to go down to UD-Q3_K_XL for Qwen 3.8 27B to get it to fit in VRAM and be usable, but I worry I'm gutting its intelligence somewhat. I too am interested in faster + more-usable alternative that can exchange blows with the Q3-dumbed 27B.

jadbox•about 2 hours ago

I need someone to run actual benchmarks between the two.

gertlabs•17 minutes ago

These models have gotten a fair amount of attention -- we're hoping it's enough to get them added to some reliable inference providers and OpenRouter, at which point we'll run them on our full benchmark suite.

swatcoder•about 2 hours ago

Benchmarks are the BMI of model evaluation.

They may have utility in trying to look at the whole landscape of models, but are very misleading when it comes to making 1:1 comparisons or in developing confidence at to how a given model will deliver on your workflow.

NitpickLawyer•43 minutes ago

Only relevant benchmarks are those you make yourself, targeted specifically for your workflows. Anything else is just number go up on a pretty graph, and every model out there is probably benchmaxxed to hell on the public ones anyway. Keep yours private.

prometheus1992•about 2 hours 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

garo-pro•about 1 hour ago

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

wgd•9 minutes ago

Nobody (with the probable exception of Anthropic given their work on character training) really trains models on their identity and Claude is the only AI persona that's well-defined so if you put yourself into the AI's shoes it's a pretty reasonable guess that it might be Claude. I've had basically every open model claim it's Claude when the topic comes up.

colingauvin•about 1 hour ago

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

kees99•41 minutes ago

Ornith-1.5-397B is derived from Qwen3.5-397B-A17B via post-training. That process preserves exact parameter count.

colingauvin•31 minutes ago

Ah thanks for the background. Well, time to learn how to quant things down!

bigcat12345678•about 3 hours 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•about 3 hours ago

It looks like they post-trained Qwen3.6. Interesting to see how far they could improve it with they harness/algorithm.

esafak•33 minutes ago

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.

nextaccountic•about 2 hours ago

Is this open weights? Or planned to be

randomblock1•about 2 hours ago

Yes: https://huggingface.co/collections/ornith-ai/ornith-15

wyre•about 1 hour ago

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.

jakswa•about 2 hours ago

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.

tangjurine•about 2 hours ago

This looks cool

htrp•33 minutes ago

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