Unverified60% confidenceFactExact time
Gemini Nano was distilled from the Gemini family of large models, with its parameter count kept in the range of 1 billion to 3 billion.
2
Sources
60%
Confidence
Long-term
Relevance
7/8/2026
First Seen
Sources
Related Claims
UnverifiedGemini 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81% similarUnverifiedGemini Nano的参数规模约为18亿（Nano-1）和32.5亿（Nano-2）80% similarVerifiedThe Gemini series supports an ultra-long context window of up to 1 million tokens.73% similarUnverifiedGemini Nano has undergone quantization and knowledge distillation processing, enabling inference on consumer-grade CPUs or mobile NPUs.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/294766API
curl https://kongchang.com/api/v1/knowledge/claims/294766MCP
get_claim(id=294766)