IFM launches K2 Horizon: six fully open models up to 375B with full training data released
HongyiWang10 · x · 2026-09-04
IFM, part of UAE's MBZUAI, released K2 Horizon, billed as the largest fully open-source model launch in AI history.
- Six models ranging from 0.9B to 375B parameters; the flagship 375B uses MoE with 23B active parameters
- Radical openness: beyond open weights, IFM published the full training record—training code, data, data recipes, intermediate checkpoints, and eval logs
- Performance: top-tier results in every size class on coding and agentic tasks, with the 0.9B, 3.7B and 7B models reportedly setting SOTA at their scales
- Available on Hugging Face with a launch page and tech blog
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