Unverified50% confidenceFactExact time
Gemma 4 31B can run on a regular consumer GPU with around 50 TOPS of compute.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026
Sources
Gemma 4 Open-Source Model Local Deployment Guide: Ollama Installation & Mobile Setup
bilibili搞机零距离-6/10/2026
Related Claims
UnverifiedGemma 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 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%72% similarUnverifiedGemma 4 26B MOE版本可在24GB显存的显卡上运行65% similarUnverifiedGemma 4 26B模型约17GB，适合24GB以上显存的显卡，编程效果最佳65% 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65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/47407API
curl https://kongchang.com/api/v1/knowledge/claims/47407MCP
get_claim(id=47407)