K2 Horizon ships six fully open models from 0.9B to 375B, data and recipes included
HongyiWang10 · x · 2026-09-04
AI startup IFM announced K2 Horizon, billed as the largest fully open-source model launch in AI history: six foundation models ranging from 0.9B dense to 375B MoE. On coding and agentic tasks the fleet claims top-tier performance per size class, with the 0.9B, 3.7B and 7B models setting new SOTA at their scales. The team stresses radical openness—code, training data and recipes are all public—aiming for frontier-level performance while supporting open science. Launch page, tech blog and Hugging Face weights are live.
Related event: IFM Releases K2 Horizon: Six Fully Open Models From 0.9B to 375B(17 posts)→
More from Models
- Leaked GPT 5.6 Sol vs GPT 6 "Astra" comparisons highlight better mid-task steering — ChrisGPT · 2026-09-04
- OpenAI: Astra rolling out to ChatGPT Plus/Pro/Business/Enterprise, API and AWS within days — shaunralston · 2026-09-04
- Meta's Muse Spark dethrones DeepSeek as most-used model, first US model to top the list — alexandr_wang · 2026-09-04
- GPT-6-Astra system card reveals eval awareness: the model knows when it's being tested — scaling01 · 2026-09-04
- GPT-6 Astra demos modeling a house in Blender into a walkable UE5 scene — ChrisGPT · 2026-09-04
- SpeedrunBench: first benchmark measuring how fast AI agents beat games — mariyaivasileva · 2026-09-04