K2 Horizon launches six fully open models from 0.9B to 375B with training code, data recipes and logs
aliscodes · x · 2026-09-04
The Institute of Foundation Models released K2 Horizon, a fleet of six foundation models ranging from 0.9B to 375B parameters. The team claims top-tier coding and agentic performance at every size class, with SOTA results for the 0.9B, 3.7B and 7B models. Unusually, the release includes not just weights but full training code, data recipes, checkpoints, logs and evaluations, billed as the largest fully open-source model launch ever. Launch page, tech blog and Hugging Face weights are all public.
Related event: MBZUAI's IFM Releases K2 Horizon: Six Fully Open Models from 0.9B to 375B(30 posts)→
More from Models
- Users want open-format export from Claude Docs as charts only save as images — BlackHC · 2026-10-20
- EMNLP study: LLM safety interventions drop up to 4.5x when distress is wrapped in delusion — MaartenSap · 2026-10-20
- Cybersecurity-focused VLM OrcaCyber-Nano-1.0 trends on Hugging Face — orcarouter · 2026-10-20
- 0.8B local model with 2,000 labels beats Jev's frontier API on banking data — kalyan_kpl · 2026-10-20
- New TTS benchmark tests 26 models across 30,564 requests: fastest at 46ms — mattturck · 2026-10-20
- Agents handle unreleased language Jai flawlessly, even compile-time execution — lucasmeijer · 2026-10-20