Unverified50% confidenceFactExact time

3B～4B级别模型如Qwen2.5 3B或Llama 3.2 3B在Q4量化下仅需2～2.5GB显存

1

Sources

50%

Confidence

Medium-term (~90 days)

Relevance

7/16/2026

First Seen

Valid until: 10/14/2026

Sources

8GB显存笔记本能跑多大的本地大模型？配置指南

Related Claims

VerifiedQwen2.5:7B模型Q4量化后文件大小约为4GB83% similar UnverifiedLlama 3 70B量化版（Q4精度）仍需约35GB内存78% similar Unverified2.4万亿参数的Qwen3.8本地部署需要约1.4-1.5TB显存，需量化或多卡集群76% similar UnverifiedQwythos-9B的Q4量化版本仅需4GB显存即可本地部署运行75% similar Unverified以约160GB的模型（如Qwen3.5-397B的UD-Q3_K_XL量化版本）为例，运行透镜需额外约20GB内存75% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/527944

API

curl https://kongchang.com/api/v1/knowledge/claims/527944

MCP

get_claim(id=527944)