{"data":{"id":"61471733-33d2-42ec-9794-c4032cf882d7","title":"Introducing Gemma 4 12B: a unified, encoder-free multimodal model","summary":"Google DeepMind introduced Gemma 4 12B, a mid-sized model with native audio inputs designed to run locally on laptops with 16GB of VRAM or unified memory. Its encoder-free architecture feeds vision and audio inputs directly into the LLM backbone, and the model is released under an Apache 2.0 license with Multi-Token Prediction drafters to reduce latency.","solution":"N/A -- no mitigation discussed in source.","labels":["industry","research"],"sourceUrl":"https://deepmind.google/blog/introducing-gemma-4-12b-a-unified-encoder-free-multimodal-model/","publishedAt":"2026-06-09T14:10:19.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"issueType":"news","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":["Google"],"affectedVendorsRaw":["Gemma 4 12B","Gemma 4","Google DeepMind","Ollama","LM Studio","Hugging Face","llama.cpp","MLX","SGLang","vLLM","Unsloth"],"classifierModel":"claude-haiku-5-5","classifierPromptVersion":"v4","summaryPromptVersion":"v2","headline":null,"headlinePromptVersion":null,"cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"epssCheckedAt":null,"kevDateAdded":null,"advisoryAliases":null,"affectedPackagesSource":null,"affectedPackagesCheckedAt":null,"patchAvailable":null,"disclosureDate":"2026-06-09T14:10:19.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":null,"aiComponentTargeted":null,"llmSpecific":true,"classifierConfidence":0.9,"researchCategory":null,"atlasIds":null}}