K2-Horizon open models
Last scan Sat Nov 21, 06:54 UTC
2 sources · single origin (IFM)
K2 Horizon is among the projects that opened up their training runs, according to a Latent Space newsletter roundup.1 The only source here covers K2 Horizon briefly, alongside Marin's release of 57 intermediate checkpoints from its 535B-A23B run, and offers no reactions or disputes specific to K2 Horizon. inference21
The K2 report compares four model sizes that were all trained on the same 22T tokens.3 It also describes a decoding adapter that the team says achieves a 2.2× speedup.4
Every sentence was checked word for word against quotes from the articles it cites. Each footnote shows its quote, unless the page already quotes as much of that article as we allow; then it links the article instead. A model wrote and arranged the sentences, and a second read checked each against its quotes (written 2026-11-20).
Sources quoted
Marin and K2 Horizon opened up their training runs.
— Latent Space, [AINews] GPT-6.2 Astra, the #2 Frontier Model is better and 20%-600% cheaper, but has mixed reviews; 6.2 Sol likely main workhorseMarin released 57 intermediate Mochi checkpoints from its 535B-A23B run.
— Latent Space, [AINews] GPT-6.2 Astra, the #2 Frontier Model is better and 20%-600% cheaper, but has mixed reviews; 6.2 Sol likely main workhorseThe K2 report compares four model sizes trained on the same 22T tokens
— Latent Space, [AINews] GPT-6.2 Astra, the #2 Frontier Model is better and 20%-600% cheaper, but has mixed reviews; 6.2 Sol likely main workhorsedescribes a decoding adapter that the team says reaches 2.2× speedup
— Latent Space, [AINews] GPT-6.2 Astra, the #2 Frontier Model is better and 20%-600% cheaper, but has mixed reviews; 6.2 Sol likely main workhorse
Who reported it
- Hugging Face Daily Papersrepeats: K2-Horizon: A Frontier Fleet of Open Source Language Models
- Latent Spacerepeats IFM: The K2 report contrasts four model scales trained on an identical 22T-token dataset, and outlines a decoding adapter said to deliver a 2.2x speedup.
Facts and takes
No checked facts or takes on this story yet.
Timeline
- · Hugging Face Daily Papers: K2-Horizon: A Frontier Fleet of Open Source Language Models
- · Latent Space: [AINews] GPT-6.2 Astra, the #2 Frontier Model is better and 20%-600% cheaper, but has mixed reviews; 6.2 Sol likely main workhorse
Built 2026-11-21 06:54 UTC. Facts and quotes say who states them, not that they are true.