Google 推出全新 Gemma 3：支援多模態、多語言與長文本的開源大語言模型
Original: Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM
Google has officially launched Gemma 3, the next generation of its open-source large language model series — a major technical leap forward…
Google 推出全新一代開源模型 Gemma 3，具備強大的多模態（視覺與語音）理解能力、廣泛的多語言支持以及長文本處理能力。本次發布涵蓋多種參數規格，並與 Hugging Face 生態系統深度整合，開發者可立即透過 Transformers、vLLM 等工具進行部署與微調，為開源社群注入強大動力。
Google has officially launched Gemma 3, the next generation of its open-source large language model series — a major technical leap forward from Gemma 2. Gemma 3 adopts the same architectural innovations and research findings as Google's flagship Gemini models, aiming to offer the open-source community a high-performance, versatile, and reliable model option.
Free shows the 3-line summary; Pro unlocks the full deep summary (~300 words) so you never have to click through.
See Pro plans →Want the original English / full article?
Read on Hugging Face Blog →Summaries are AI-generated; the original article is authoritative.