Today IFM is releasing K2 Horizon, a connected fleet of six models: 375B-A23B, 36B-A4B, 32B, 7B, 3.7B, and 0.9B. Across reasoning, mathematics, coding, agentic tasks, and general capabilities, K2 Horizon delivers top-tier performance in every size class—with the 0.9B, 3.7B, and 7B models setting new state of the art at their respective scales.

We are releasing intermediate checkpoints, training data or detailed data-construction recipes, open architecture, mixture compositions, training code, configurations, fine-grained logs, evaluation results, and final weights.

The models and code are released under the Apache 2.0 license. Datasets are released under their applicable licenses, such as ODC-BY; We disclose how the data was constructed and mixed when redistribution is not possible.

you are viewing a single comment's thread
view the rest of the comments
[–] 11 points 10 hours ago (1 child)

Llama.cpp of course! After I did the switch, never looked back. Add llama-swap in front of you switch between models often.

  • source
  • parent
  • hideshow 2 child comments
  • [–] 8 points 10 hours ago* (2 children)

    llama-server has router mode built-in; you don't need separate software to swap models. I keep a list of my models in a presets.ini file.

  • source
  • parent
  • hideshow 4 child comments
  • [–] 3 points 7 hours ago (1 child)

    Yes but llama server does not unload models to fit a different model. At least, didn't managed to have just llama.cpp swap between models that fill up my vram... The second one would fail load.

  • source
  • parent
  • hideshow 2 child comments
  • [–] 1 point 7 hours ago (1 child)

    Ah. I POST to '/models/unload' when I switch models as part of my tooling -- if llama-swap is doing that for you, then I get why you'd want it.

  • source
  • parent
  • hideshow 2 child comments
  • [–] 2 points 7 hours ago*

    Yes, llama swap also give you a pretty web based statistics of all the calls and runs for every model with t/s and more statistics.

    It's pretty neat... You can also load and unload models manually, define groups for models that fit together in vram and so on.

    It gives you that automation that people coming from ollama are used to.

    under the hood all it does is running llama serve. You convert your models.ini to a yaml file 1:1 (plus a few more flexibility).

  • source
  • parent