A continual pre-train on 15T tokens. Furthermore, this model is also multimodal! People on Twitter have replaced Claude 4.5 Opus with K2.5 for tasks that need a less capable but cheaper model. However, the writing capabilities that K2 and its successor were known for have suffered in favor of coding and agentic abilities.
Specs
Params1T (32B Active)
LicenseModified MIT
Tags
modelsmodels/llmsmodels/llms/multi-modalmodels/llms/reasoningartifacts/18curated/our-picks
Related Models
