AIBase
Home
AI NEWS
AI Tools
GEO & AEO
MCP
AI Models
EN

AI News

View More

16GB Memory, Local Instant Response! Google Releases Gemma 4 12B Revolutionary Encoder-Free Architecture Ignites Open Source Community

Google releases a new multimodal model Gemma 4 12B, revolutionizing the traditional architecture by eliminating the separate encoder component, achieving efficient local deployment and inference on consumer-level hardware. This breakthrough significantly reduces the computational complexity of multimodal models, improves processing speed, and marks a new stage in the open source large model ecosystem.

19.4k 5 hours ago
16GB Memory, Local Instant Response! Google Releases Gemma 4 12B Revolutionary Encoder-Free Architecture Ignites Open Source Community

Google Releases Open-Source Gemma412B Model: Focuses on Encoder-Free Multimodal with 16GB Memory Notebook for Local Execution

Google releases new open-source large model Gemma412B with a unified encoder-free architecture, enabling on-device full-modal AI. It directly processes text, images, audio, and video in a single Transformer backbone, eliminating memory and latency issues from external encoders.....

15.4k 2 days ago
Google Releases Open-Source Gemma412B Model: Focuses on Encoder-Free Multimodal with 16GB Memory Notebook for Local Execution

Models

View More

ENEL

IvanTang

E

ENEL is a model exploring the potential of encoder-free architecture in 3D large multimodal models.

MultimodalPytorchPytorch
IvanTang
17
1
AIBase
Empowering the future, your artificial intelligence solution think tank
English简体中文繁體中文にほんご
FirendLinks:
AI Newsletters AI ToolsMCP ServersAI NewsAI MarketingLLM LeaderboardAI Ranking
© 2026AIBase
Business CooperationSite Map