Join the discussion
Write your take first — we'll ask for email only when you're ready to publish.
- Hacker News
- Weird they talk about their 31B dense model but haven't actually released it anywhere.by smcleod
- Why don't these 'self-improving' ones eventually improve to the point of being better that the bleeding edge?by LoveMortuus
- I've used a lot of local models and all of them felt like toys. This one actually felt useful. I hear Qwen 36-A3B is also good, yet to try that one.by fareesh
- Self-Improving bullshit. It is just Qwen 3.5 finetune benchmaxxed . Nothing spectacular . even fails at benchmarks. Long session tool calls sucks and hallucinate a lot with that too. Just use Qwen 3.6 and 3.5 122b.by v3ss0n
- > the dense 9B fits on a single 80GB GPU
Us mere mortals cannot use this.
- There are already quantizations availableby armarr
- Seems weird. A 9B model would normally fit unquantised on a 24GB GPU.by regularfry
- These are simply benchmaxxed versions of either Qwen or Gemma 4.by S0y
- Citation neededby jorisw
- If so, it's impressive they managed to benchmaxx Qwen even further than it's already benchmaxxed.by 2001zhaozhao
- I've been testing Ornith-1.0 35B (my own FP8-block quant) and I like it. It runs at >200 tok/s w/ vLLM on an RTX PRO 6000 (sm120), I've run >140M cached tokens of agentic coding work on it over the past few days. It seems to about somewhere between Qwen 3.6 35B-A3B and 27B, but the good thing: it overthinks/doom-loop a lot less than Qwen 3.6. When looking at the thinking traces I like its breakdown approach template.
It does good job on basic analysis, tasks, and some front-end/backend changes on a medium-sized Go codebase, but it reached its limits totally botching a longer (simple) kernel implementation job (about 100 iterations in Pi Agent harness) - this is the type of thing that stronger open models (Kimi K2.6, GLM 5.2) are able to do.
by lhl - With this model size I've found that the harness seems to matter more. I've moved on to little-coder rather than raw pi with qwen3.6 27b personally, it might be worth taking a look.by regularfry
- Can anyone explain what’s the story here? Is this just a re-skinned qwen? Who is deepreinforce-ai and why isn’t this model listed on their website?
How does it self-improve, does the model change on disk - or just during a single context run it gets better?
by kennywinker - Clickbait title.by v3ss0n
- It doesn't self-improve, that's a misleading headline.
As far as I can tell they trained it by running their own reinforcement learning on top of Qwen and Gemma 4 (not sure how they combined weights from both, or if they used Qwen as the basis and Gemma 4 to help train?) - so the "self-improving" is about their training process, not how you use the weights.
by simonw - From what I personally tested Ornith-1.0 35B is slightly better than Qwen-3.6 35B. My tests are tasks that consist of adding/modify feature in a big C++ codebase. The part that I find interesting is that the model is way faster than Qwen3.6 35B. It seems Ornith produce a smaller chain of thought. On my test it can be 3 time faster to produce the answer.
I use it via llamacpp and codex-cli.
by Narew - This is the first Qwen fine-tune that is not immediately rejected by the local LLM community, and in some cases even being recommended. Based on my limited usage, it is good, gives creative solutions to coding problems. I don't expect 9-35B models to one-click create full apps. Most people who were complaining did so .by ricardobayes
- We must be in different communities... Qwen models are the most recommended ones that will actually run on local hardware that is accessible to the masses!
- Its not any better. Most of us at LocalLLama community dont like it except a few new people poping out and making posts.by v3ss0n
- > Most people who were complaining did so .
It has been this way since the beginning, unfortunately. There is certainly no harm in trying on local models on local workloads with modest guardrails.
Like most of these models (Qwen, Gemma, Llama, gpt-oss), finding all the little gotchas like, special tokens and prompt structure, model preference are a PITA right now. The reward are really nice models that run exceptionally well in agentic harnesses tuned with the prompts and parameters you fought so hard to learn.
by monkmartinez - The local LLM community is now teeming with erstwhile crypto and NFT hucksters who've brought the culture of hype from their former communities with them. There still are a few deeply technical people left, but their voices are being crowded out by the vapid marketers'.
- Previously: https://news.ycombinator.com/item?id=48709744
https://swelljoe.com/post/will-it-mythos/: "Poor performer here, only found the one bug that almost every model found, despite its performance on other benchmarks being excellent for its size. […] It also performs poorly in a chat without tools, exhibiting an ehthusiasm for hallucination. I’m currently working on a replication of this with full tool access, including bash/Python, which may allow this model to be competitive."
by CharlesW - That benchmark ranks Kimi K2.6 and K2.7 Code near the bottom. Both are below Ornith 35B. It ranks Gemma 4 26B much higher than GLM-5.2. The results don't make much sense.
- > It also performs poorly in a chat without tools, exhibiting an ehthusiasm for hallucination. I’m currently working on a replication of this with full tool access, including bash/Python, which may allow this model to be competitive.
How is that a serious phrase in '26? I mean I have no idea if this fine-tune is good, haven't tried it, but testing a (clearly) agentic model without tool access and expecting it to work is crazy, no? What was he even testing?!