IFM open-sources K2 Horizon fleet: six LLMs from 0.9B to a 375B MoE
tw_killian · x · 2026-09-04
IFM released the K2 Horizon collection on Hugging Face — six open LLMs at once: 0.9B, 3.7B, 7B, 32B dense, 36B MoVA (A4B), and a 375B MoE (A23B), with GGUF and FP8 quantized variants.
- Also open-sourced "Uno" adapters (7B/0.9B) for fast diffusion decoding.
- Ships with extensive training data (TxT360 v2, Code/Math/SFT Reasoning, Pretrain-Behaviors), training logs, and intermediate checkpoints for pre-training, mid-training, and post-training — maximal reproducibility.
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