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 Radically Open Models up to 375B(11 posts)→
More from Models
- OpenAI Teases Mystery Project 'Astra' as Release Nears — koltregaskes · 2026-09-04
- Marin's open 535B-A23B model is 13% trained, funded by Huang Foundation — dlwh · 2026-09-04
- Sentdex: GPT 5.6 solves quadruped robot tasks but takes 4-20+ minutes — Sentdex · 2026-09-04
- OpenAI repo: GPT-6-Astra Lean-formalizes proof of primes within distance 186 — scaling01 · 2026-09-04
- Respan launches P-1 privacy model, beats AWS on PII detection F1 across benchmarks — CodeByPoonam · 2026-09-04
- OpenAI repo claims GPT-6-Astra Lean-formalized a prime-gaps bound of 186 — scaling01 · 2026-09-04