Unverified50% confidenceReleaseExact time
Recursive released Ripple 65B Preview, a 65-billion-parameter dense model under the Apache 2.0 license, pretrained on 12 trillion tokens and supporting up to 1 million tokens of context.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/13/2026
First Seen
Valid until: 2/11/2027
Sources
Related Entities
Related Claims
UnverifiedRipple-65B was trained from scratch using 12 trillion tokens of text and code, with a context window reaching 1 million tokens.75% similarUnverifiedKolibri uses a Mixture of Experts (MoE) architecture with approximately 78 billion total parameters, activating only approximately 3.46 billion parameters per token, and is open under the Apache 2.0 license.67% similarUnverifiedNCP-ArchPreview scales to 8.9 billion parameters and is trained on 5.73 trillion tokens of the Dolma-3 dataset.65% similarUnverifiedVibe prospecting integrates more than 50 data sources, covering 150 million company profiles and 800 million personal profiles.62% similarUnverifiedBaidu open-sourced the base model of ERNIE EIE 5.5 Flash, with 280 billion total parameters, 14 billion activated each time, a maximum context of 1 million tokens, and it has not yet undergone instruction fine-tuning.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1166483API
curl https://kongchang.com/api/v1/knowledge/claims/1166483MCP
get_claim(id=1166483)