{"slug": "rio-de-janeiro-s-homegrown-llm-appears-to-be-a-merge-of-an-existing-model", "title": "Rio de Janeiro's \"homegrown\" LLM appears to be a merge of an existing model", "summary": "Rio de Janeiro's city government released a large language model called Rio-3.5-Open-397B, claiming it was originally trained by IplanRIO. However, an investigation reveals the model is a direct element-wise merge of Nex-AGI's Nex-N2 model and Qwen's Qwen3.5-397B-A17B, with no evidence of independent training. The model identifies itself as Nex 79% of the time and recites Nex-AGI's backstory word-for-word.", "body_md": "-\n[Notifications](/login?return_to=%2Fnex-agi%2FNex-N2)You must be signed in to change notification settings -\n[Fork 11](/login?return_to=%2Fnex-agi%2FNex-N2)\n\n# Rio-3.5-Open-397B ≈ 0.6 x Nex-N2_pro + 0.4 x Qwen #4\n\nCopy link\n\nCopy link\n\nOpen\n\n## Description\n\n[ prefeitura-rio/Rio-3.5-Open-397B](https://huggingface.co/prefeitura-rio/Rio-3.5-Open-397B) is presented as an original 397B model trained by\n\n[IplanRIO](https://iplanrio.rio.rj.gov.br/). It is not. Its weights are a\n\n**direct element-wise merge of our model, Nex, with the official**— about\n\n[base](https://huggingface.co/Qwen/Qwen3.5-397B-A17B)`Qwen3.5-397B-A17B`\n\n**0.6 Nex / 0.4 Qwen**— and we find\n\n**no evidence of any training of their own.** We can show this\n\n**two completely independent ways**:\n\n**With Rio's hard-coded \"You are Rio\" system prompt removed, its own deployed model identifies itself as \"Nex, from Nex-AGI\" 79% of the time — and as \"Rio\" 0% of the time.**It even recites our organization's bespoke backstory word-for-word.** Every weight tensor in Rio is, to thousands of standard deviations, the same 0.6/0.4 blend of Nex and Qwen**— across all 60 layers and every component of the network. Other finetunes cannot be explained as interpolations.\n\nBelow is the evidence. Judge for yourself.\n\nReactions are currently unavailable\n\n## Metadata\n\n## Metadata\n\n### Assignees\n\n### Labels\n\nNo labels\n\n### Type\n\n### Fields\n\n[Give feedback](https://github.com/orgs/community/discussions/189141)\n\nNo fields configured for issues without a type.", "url": "https://wpnews.pro/news/rio-de-janeiro-s-homegrown-llm-appears-to-be-a-merge-of-an-existing-model", "canonical_source": "https://github.com/nex-agi/Nex-N2/issues/4", "published_at": "2026-06-14 15:37:31+00:00", "updated_at": "2026-06-14 15:42:31.978459+00:00", "lang": "en", "topics": ["large-language-models", "ai-ethics", "ai-research"], "entities": ["Rio-3.5-Open-397B", "Nex-N2", "Qwen3.5-397B-A17B", "IplanRIO", "Nex-AGI", "prefeitura-rio"], "alternates": {"html": "https://wpnews.pro/news/rio-de-janeiro-s-homegrown-llm-appears-to-be-a-merge-of-an-existing-model", "markdown": "https://wpnews.pro/news/rio-de-janeiro-s-homegrown-llm-appears-to-be-a-merge-of-an-existing-model.md", "text": "https://wpnews.pro/news/rio-de-janeiro-s-homegrown-llm-appears-to-be-a-merge-of-an-existing-model.txt", "jsonld": "https://wpnews.pro/news/rio-de-janeiro-s-homegrown-llm-appears-to-be-a-merge-of-an-existing-model.jsonld"}}