Verified65% confidenceFactTime unknown
Gemma 4的1B/2B模型量化后仅需4GB显存即可运行
3
Sources
65%
Confidence
Long-term
Relevance
6/3/2026
First Seen
Sources
Google Gemma 4实测：手机离线运行+Ollama部署教程
bilibiliAGI_Ananas
Related Entities
Related Claims
UnverifiedGemma 3 12B的FP16版本约需24GB显存，Q4_K_M版本降至约7-8GB，推理速度提升约2-3倍，结构化输出准确率仅损失约2-5%76% similarUnverifiedGemma 4 26B模型约17GB，适合24GB以上显存的显卡，编程效果最佳76% similarUnverifiedGemma 4 31B 经量化后模型大小约为 20GB，实测 GPU 显存占用约 20.5GB，GPU 利用率约 91%74% similarUnverifiedGemma 4 26B MOE版本在24GB显存GPU上实际推理速度达到每秒60个Token73% similarUnverifiedGemma 4 26B MOE版本可在24GB显存的显卡上运行71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/38370API
curl https://kongchang.com/api/v1/knowledge/claims/38370MCP
get_claim(id=38370)