Unverified50% confidenceFactExact time
典型的端侧LLM如Google Gemini Nano、微软Phi-3 Mini参数量通常控制在1B-4B范围内
1
Sources
50%
Confidence
Long-term
Relevance
8/26/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedGoogle's Gemini Nano is designed for on-device deployment with a parameter scale of approximately 1.8B–3.2B.78% similarUnverifiedGemini Nano是参数量在1.8B至3.25B之间的端侧小模型，支持断网状态下执行语音指令理解、导航意图识别等核心任务74% similarUnverified谷歌针对车载场景优化了Gemini Nano端侧小模型，参数量在1.8B至3.25B之间，支持断网状态下执行语音指令理解73% similarUnverifiedGemini Nano的参数量在数十亿量级，而主流云端大语言模型如GPT-4、Gemini Ultra参数量通常在数千亿量级71% similarUnverifiedThe model is very likely Google's local version of Gemini Nano.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/803582API
curl https://kongchang.com/api/v1/knowledge/claims/803582MCP
get_claim(id=803582)