Birbla

Join the discussion

Write your take first — we'll ask for email only when you're ready to publish.

Sign in
  • Hacker News
  • 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.

    by wyre
  • 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

    by AIorNot
  • The former
    by kzrdude
  • 397 is just too big for two Sparks even at NVFP4. Wish they had made this just a tiny bit smaller.
    by colingauvin
  • Ornith-1.5-397B is derived from Qwen3.5-397B-A17B via post-training. That process preserves exact parameter count.
    by kees99
  • Please check your download links, it get 400 Bad Request on https://huggingface.co/ornith-ai/Ornith-1.5-397B-GGUF/tree/m...

    only mmproj can be downloaded right now

    by readyblue
  • 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!

    by hxii
  • 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!
    by lsb
  • It's somewhat close, but a lot worse at code it seems. Qwen 3.8 is a wild improvement over 3.6.

                                   Qwen 3.8-27B     Ornith-1.5-35B
    
    Terminal-Bench 2.1         73.0             67.8
    SWE-bench Pro              61.7             59.6
    DeepSWE (1.1)              42.2             22.0
    NL2Repo                    42.3             46.2
    GPQA Diamond               89.2             89.2
    Humanity's Last Exam       30.8             25.6
    by ricardobeat
  • 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.
    by jonesy827
  • I need someone to run actual benchmarks between the two.
    by jadbox
  • 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.
    by jakswa
  • What you say is in agreement with someone I follow on X. My family has been traveling for two weeks and I have been looking forward to trying qwen3.8-37b when I get home.

    Now I might try Ornith-1.5-35B first even though I don’t see an official MLX version.

    by mark_l_watson
  • 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.
    by bigcat12345678
  • It looks like they post-trained Qwen3.6. Interesting to see how far they could improve it with they harness/algorithm.
    by goldemerald
  • 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
    by prometheus1992
  • What did you use it for? I've found it somewhat capable but not worth to actually use it (1 9B, that is)
    by _def
  • 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.

    by esafak
  • 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.
    by montroser
  • The way it was said made it sound like they had something better than a 35B-A3B coming.
    by hgoel
  • I'm running qwen3.8 27B dense on reasonable hardware (oem spark)

    tbh, I have stopped using MoE in the name of speed, the dense (with more active parameters) makes a real difference in output quality

    by verdverm
  • I've been experimenting with it on a M4 Pro 24G for the last few hours and it's been very promising using 32k context. getting around 30-40 tps

    With Qwen3.8 27B I could not get anywhere near 32k context window, that made it very unusable for agentic coding, although it was very smart.

    by huseyinkeles
  • > The MoE architecture makes a huge difference for being able to run these local models on reasonable consumer hardware

    That's not true. For computers without unified memory architecture (which is the vast majority) VRAM capacity is the bottleneck for local models. In that case a dense model can deliver significantly more intelligence than an MoE model of the same size. And for a typical consumer/gamer Nvidia GPU, dense models are fast enough.

    by Sha1rholder
  • 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.
    by mirekrusin
  • 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.

    by dofm
  • The smarter 27B is so fast with MTP I've found I really don't need the 35B-A3B. You get around 70tk/s on a M5 Max lowering to around 40tk/s at higher context sizes.
    by smcleod
  • 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.

    by parsimo2010