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.
More from Models
- OpenAI launches GPT-6 Astra, claiming it can do anything you do on a computer — kagigz · 2026-09-04
- Databricks evals: GPT-6 Astra claims SOTA on OfficeQA Pro benchmarks, cheaper per task — downingARK · 2026-09-04
- Mathematician tests GPT-6 Astra: live Lean proof verification while writing arguments — teortaxesTex · 2026-09-04
- Tavus Launches Sparrow-2, Claiming #1 in End-of-Turn Detection and Interruption Handling — ycombinator · 2026-09-04
- ARC-AGI-3: 10x reasoning tokens cuts total cost from $48k to $26k vs medium — i_dg23 · 2026-09-04
- Researchers flag data contamination concerns in benchmark behind Astra's time-horizon score — dfrsrchtwts · 2026-09-04