IFM open-sources K2 Horizon models from 0.9B to 375B with training code and data recipes
testingcatalog · x · 2026-09-03
IFM has released its K2 Horizon model collection on Hugging Face, shipping not just weights but also the training code, data recipes, intermediate checkpoints, logs, and evaluations behind them.
The family spans 0.9B up to 375B (MoE, A23B active), with FP8 and GGUF variants, plus datasets like TxT360-v2 and Code/Math-Reasoning SFT sets.
Two architecture pieces ship alongside:
- MoVA: routes experts inside attention itself
- Uno: a diffusion adapter that generates token blocks in parallel
A rare fully reproducible open-source package, from data to weights to training logs.
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