AIHacker Newsabout 4 hours ago
Rio LLM is a merge of existing models
1 min read
Rio-3.5-Open-397B, presented as an original 397B model by IplanRIO, is a direct element-wise merge of Nex-N2_pro and Qwen3.5-397B-A17B at a 0.6 to 0.4 ratio. No evidence of any original training was found. The discovery was made through two independent verification methods.
Level
Hype check
Tap to vote and see what everyone thinks.
