Unverified50% confidenceFactExact time
Gemma 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%
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026
Sources
Gemma 4开源模型本地部署教程：Ollama安装与手机端运行指南
bilibili搞机零距离-6/10/2026
Related Claims
UnverifiedGemma 4 26B模型约17GB，适合24GB以上显存的显卡，编程效果最佳79% similarUnverifiedGemma 4 26B MOE版本在24GB显存GPU上实际推理速度达到每秒60个Token78% similarUnverifiedFlux 2的9B参数模型在FP16精度下模型权重约占18GB显存，通常需要24GB以上的GPU显存78% similarUnverifiedGemma 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%77% similarUnverified消费级 GPU 如 RTX 4090 拥有 24 GB 显存，可运行数十亿参数的量化模型76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/47981API
curl https://kongchang.com/api/v1/knowledge/claims/47981MCP
get_claim(id=47981)