Hugging Face 推出更輕量 SmolVLM：全新 256M 與 500M 超小視覺語言模型登場！
Original: SmolVLM Grows Smaller – Introducing the 256M & 500M Models!
Hugging Face has officially introduced the newest members of the SmolVLM family, pushing vision-language model (VLM) sizes even further…
Hugging Face 發表了 SmolVLM 家族的最新成員：256M 和 500M 參數的超小型視覺語言模型（VLM）。這兩款模型體積極小，旨在讓多模態 AI 能在手機、物聯網設備或瀏覽器中流暢運行。儘管尺寸迷你，它們在基礎圖像描述與問答任務上仍展現出實用的性能，為邊緣端多模態應用開闢新路徑。
Hugging Face has officially introduced the newest members of the SmolVLM family, pushing vision-language model (VLM) sizes even further down to 256M (256 million) and 500M (500 million) parameters. This release marks a significant step forward for multimodal AI toward edge and local deployment.
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.