--- title: Nemotron 3.5 Content Safety: Customizable Multimodal... description: NVIDIA releases Nemotron 3.5 Content Safety, a 4B-parameter multimodal safety model built on Google Gemma 3 4B IT. Key additions over Nemotron 3 include... canonical: https://daily.dev/posts/nemotron-3-5-content-safety-customizable-multimodal-safety-for-global-enterprise-ai-0rk6fvwun twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Nemotron 3.5 Content Safety: Customizable Multimodal Safety for Global Enterprise AI | daily.dev og:description: NVIDIA releases Nemotron 3.5 Content Safety, a 4B-parameter multimodal safety model built on Google Gemma 3 4B IT. Key additions over Nemotron 3 include... og:url: https://daily.dev/posts/nemotron-3-5-content-safety-customizable-multimodal-safety-for-global-enterprise-ai-0rk6fvwun og:image: https://api.daily.dev/og/posts/0rk6Fvwun.png og:image:alt: Nemotron 3.5 Content Safety: Customizable Multimodal Safety for Global Enterprise AI og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Nemotron 3.5 Content Safety: Customizable Multimodal Safety for Global Enterprise AI **[Hugging Face](https://daily.dev/sources/huggingface)** · 11 min read · 0 upvotes · 0 comments ## Summary NVIDIA releases Nemotron 3.5 Content Safety, a 4B-parameter multimodal safety model built on Google Gemma 3 4B IT. Key additions over Nemotron 3 include unified multimodal evaluation (user prompt + image + assistant response in one pass), custom enterprise policy enforcement at inference time, auditable reasoning traces via THINK mode, and coverage across 12 explicitly trained languages plus ~140 via zero-shot transfer. The model supports three output modes ranging from low-latency binary verdicts to full reasoning traces, uses the Aegis 2.0 taxonomy (13 core + 10 subcategories), and achieves ~85% average accuracy across multilingual and multimodal benchmarks with 3x lower latency than comparable multimodal safety models. NVIDIA is also releasing the training dataset, a rarity in the multimodal safety space. The model is available on Hugging Face under NVIDIA Open Model License and as a production NIM microservice. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Nemotron 3 Content Safety 4B: Multimodal, Multilingual Content Moderation](https://daily.dev/posts/nemotron-3-content-safety-4b-multimodal-multilingual-content-moderation-jdpzsohgf) · Hugging Face · 0 upvotes · 0 comments - [Building NVIDIA Nemotron 3 Agents for Reasoning, Multimodal RAG, Voice, and Safety](https://daily.dev/posts/building-nvidia-nemotron-3-agents-for-reasoning-multimodal-rag-voice-and-safety-kmj8nolvr) · NVIDIA Developer · 1 upvotes · 0 comments - [Run Multimodal Reasoning Agents with NVIDIA Nemotron on vLLM](https://daily.dev/posts/run-multimodal-reasoning-agents-with-nvidia-nemotron-on-vllm-vumht6rln) · vLLM · 0 upvotes · 0 comments - [Custom Policy Enforcement with Reasoning: Faster, Safer AI Applications](https://daily.dev/posts/custom-policy-enforcement-with-reasoning-faster-safer-ai-applications-skp3uh6zl) · Hugging Face · 1 upvotes · 0 comments --- Tags: [#nvidia](https://daily.dev/tags/nvidia), [#multimodal](https://daily.dev/tags/multimodal), [#gemma](https://daily.dev/tags/gemma) [View this post on daily.dev](https://daily.dev/posts/nemotron-3-5-content-safety-customizable-multimodal-safety-for-global-enterprise-ai-0rk6fvwun) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Nemotron 3.5 Content Safety: Customizable Multimodal Safety for Global Enterprise AI","url":"https://daily.dev/posts/nemotron-3-5-content-safety-customizable-multimodal-safety-for-global-enterprise-ai-0rk6fvwun","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/nemotron-3-5-content-safety-customizable-multimodal-safety-for-global-enterprise-ai-0rk6fvwun"},"datePublished":"2026-06-04T19:01:05.987Z","dateModified":"2026-06-04T19:01:32.116Z","description":"NVIDIA releases Nemotron 3.5 Content Safety, a 4B-parameter multimodal safety model built on Google Gemma 3 4B IT. Key additions over Nemotron 3 include...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/604334663058182de50674847b607afc?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/604334663058182de50674847b607afc?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Hugging Face","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Hugging Face","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/f1f55c67d81a4330acf5b90b26b0c8e1","url":"https://daily.dev/sources/huggingface"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/nemotron-3-5-content-safety-customizable-multimodal-safety-for-global-enterprise-ai-0rk6fvwun","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"nvidia,multimodal,gemma","timeRequired":"PT11M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Hugging Face","item":"https://daily.dev/sources/huggingface"},{"@type":"ListItem","position":3,"name":"Nemotron 3.5 Content Safety: Customizable Multimodal Safety for Global Enterprise AI"}]} ```