Tag
Quantized versions of the K2-Horizon AI model series are now available for download on Hugging Face, supporting various sizes from 0.9B to 36B parameters. However, the llama.cpp support is still in progress, requiring a fork for use.
The k2 horizon AI models, particularly the 7B variant, are praised for outperforming muse glimmer despite smaller size, with full open-sourcing that could set a new standard if benchmarks are accurate.
IFM AI's K2-Horizon-400B-MoE continues to outperform Thinking Machine's Inkling on Artificial Analysis benchmarks, according to a team member highlighting the year-old lab's progress.
IFM AI introduces K2 Horizon, a fully open-source fleet of six foundation models ranging from 0.9B to 375B parameters, claiming frontier performance in coding and agentic tasks. The release is touted as the largest fully open-source model launch in AI history, with complete transparency and open access to training data and code.