Unverified50% confidenceFactExact time
最新模型的上下文长度已达128K token
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026
Sources
ChatGPT与Codex合体：能自主工作24小时的AI助手意味着什么
bilibili品信智慧6/6/2026
Related Claims
Verified此前主流模型的上下文长度通常在8K到128K之间82% similarVerified当前主流模型的上下文窗口约为128K至100万Token75% similarUnverified当前最先进的大语言模型已经支持128K甚至200K的上下文长度71% similarUnverified典型7B模型（32层、32头、128维度）在FP16精度下处理2048 token序列、批大小8时，KV Cache约消耗4GB显存67% similarUnverifiedRTX 5090上Qwen3.6 27B模型预填充速度从174提升到253 token/s，显存占用约18GB67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/52661API
curl https://kongchang.com/api/v1/knowledge/claims/52661MCP
get_claim(id=52661)