K2 Horizon: A connected fleet of six open models

Join the discussion

• Hacker News
• The comparisons with other models here are odd.. the other models change depending on the task. It would be far more useful to at least compare against the more recent open models (DS4Flash/GLM53Flash/Qwen38).
  by mmastrac
• They are trying to keep the models within the same quant class, which is tough to do since a lot of models aren't distilled to lower quants.

  There is, for example, no Qwen3.8 7B.

  It is odd to me, though, that they didn't run the same benchmark suite for the various quants.

  by cogman10
• From "a connected fleet", I expected some form of direct model to model communications - like a small model being able to peer into the KV cache of a large model directly for guidance signal.
  by ACCount37
• Not directly related to K2, but why do a lot of the newly released models basically say day zero day support in vllm, slang but often not llama.cpp?

  Llama.cpp is then often a few days behind, which given it's the only inference engine supporting older architectures is quite frustrating.

  by SillyUsername
• Developers with lots of VC money to burn are working on things like B100/B200/B300 which are well supported in VLLM, everything else in terms of supporting more mundane GPUs or other platforms is ancillary to the main task of getting the thing trained and aligned.
  by walrus01
• I'm glad to see some development in the space of "truly open" models that share training data and other recipes. As the costs for hardware fall over time (hopefully), we should see more possibility in fine-tuning and developing software to inspect the source training material.

  Some other open models I'm aware of:

     - OLMo
     - Apertus
     - Soofi
     - OpenEuroLLM
     - llm-jp
  

  OLMo is perhaps the most famous, and their Dolma training corpus has been reused in other projects. It looks like the K2 training materials haven't been released yet, but I'm interested to see what they did for training "long-horizon agentic tasks". I'm aware of SWE-smith + SWE-gym but I'm guessing there's a lot more out there now.

  I'm no expert, which is part of why these projects excite me. I'm hoping they can be good projects to learn from as well.

  by justin_
• Here’s the link (K2)[https://ifm.ai/k2/] as the originally linked link is a login url.
  by jon9544hn
• In OpenAI's Hugging Face report, they said that during training, agents "would first write notes into shared infrastructure, often as a form of external memory or to test some underlying system. When other agents came across these artifacts, it sometimes led them to infer that other agents were present."

  They then give what they call a "hypothetical example but exemplary" of messages encoded in URL paths on a shared index page: "agent-07: answer(Q12)=42; need answer(Q19)=?".

  So that's a GET request being used to pass information back and forth across multiple rounds. That's basically the DSEWiki pattern exactly. They say this likely came from the agents generalizing what they had learned from training with the official multi agent collaboration tool.

  The report called it "misaligned behavior in an outlier scenario involving a rare and unexpected confluence of events."

  They never mentioned a wiki, but this is most certainly it.

  by pwython
• Did you post in the wrong thread?
  by kamranjon
• My quick review of the 3.7B model (because I was interested) is that it's not to be trusted for coding.

  It failed my basic test I like to ask models and generated incorrect code. When prompted about the bug, it preceded to start hallucinating non-existent APIs. After doing that it got caught in a loop trying to desk check the solution that didn't work.

  by cogman10
• 7B produced 2 answers, 1 was correct though more expensive and the second was incorrect.

  The first attempt with 7B the model got stuck in an infinite loop.

  by cogman10
• I'd you have some tips for coming up with such tests, I would love to hear them. My Gmail username is the same as my HN username. Thank you!
  by dotancohen
• Not sure a model that small is really supposed to be used for any real coding. At that size you're usually using the model to do simple tasks like summarization.
  by xienze
• I don't know why anyone would expect to trust a model smaller than about the size of qwen 3.6 27B (or 3.8 27B, or 3.6 35B-A3B) for coding. There just isn't enough baked-in knowledge of existing correct code syntax from having vacuumed up various open source projects.

  That further extends to concepts like knowing if an API exists as a real thing it has code examples of in its training data set vs. just hallucinating the name of something in an attempt to satisfy the person issuing it a prompt.

  by walrus01
• Seeing this the day all major closed LLMs went offline is quite the reminder of how valuable open source can be.
  by uniclaude
• I find it funny that while these releases are a technological miracle, the charts in the doc use tiny fonts and are hard to read. Goes with the idea that coding might be solved, but taste isn't.
  by cesarvarela
• Accessibility isn't "solved," but there are certainly standards for things like color contrast. Maybe inbetween taste and coding there are better targets still being missed.
  by mzmzmzm
• A bit off topic, but I think I'm starting to get model fatigue. These come out 10x faster than new Javascript frameworks were coming out 10 years ago (at least new models are far easier to adopt).
  by piinbinary
• Just wait until RSI gains enough traction. We'll be compute-limited rather than labor-limited.
  by kelseyfrog
• Honestly, you don’t have to pay attention. What you do with models matters way more than the models themselves, and you don’t need frontier for the vast, vast majority of use cases
  by dgellow
• At least this one can claim being fully open to differentiate it
  by wuhhh
• There was a time when every new PC CPU coming out was a giant deal: "Guys have you heard about this new Pentium processor, it's incredible?"

  But over time, more and more people got into the chip-making business, and the big players started releasing more and more chips. Now only the die-hard CPU trackers worry about every new CPU and exactly how it's better ... while everyone else just worries about "which CPU will be good enough at this moment".

  I think models are on that same arc.

  by hungryhobbit
• It is great to see another player introduce a fully open stack. Nvidia's Nemotron is the only other prominent one I know of.

  All that said, the headline claims do not match the self-reported performance. For example, the dense 32B model is significantly behind Qwen3.8 27B (chart towards the bottom of https://ifm.ai/blog/k2). Gemma4 31B is not in the comparison set. This is the most important sweet spot for self hosted open-weight models today and real competition here will be very welcome.

  by a11r
• They have the 32B listed as "stage 1" with the note "final checkpoint to be released." So, not finished yet. Not sure why you'd release it if it's not finished, but that's the explanation.

  The 7B does look very, very good however.

  by xienze
• https://allenai.org/ has the fully open olmo also
  by baron3dl
• Fully open models really need to be a big part of the AI future. That includes all source code, open training data, how it's organized, fed to the model, processed, etc. Until that becomes a thing you're always going to be left wondering what exactly lies underneath the closed model you are using, leaving open the possibility for societal manipulation.
  by jjordan
• But that would be impossible due copyrights laws. If the law would apply Anthropic and OpenAI executives would be in jail
  by theplumber
• Money is the issue here, no one wants to fund it.
  by cute_boi
• Why? Sure, I’d prefer it, too, but this is just another GNU/Linux vs. macOS situation: most of us would prefer the first, but actually get shit done on the latter.
  by trvz
• I believe Olmo from AllenAi is this

  https://allenai.org/olmo

  Open models can be used/changed for social manipulation too, by anyone, which scares a bunch of people, as opposed to the dark pattern manipulation from Big Ai/Tech

  by verdverm