Unverified50% confidenceFactExact time

DeepSeek-R1 7B 的上下文窗口通常可达 128K Tokens，但本地实际可用长度受限于显存容量

1

Sources

50%

Confidence

Medium-term (~90 days)

Relevance

7/19/2026

First Seen

Valid until: 10/17/2026

Sources

Ollama Modelfile实战：本地部署专属DeepSeek-R1自定义模型

Related Claims

UnverifiedDeepSeek的上下文窗口通常为64K-128K tokens，约相当于5-10万中文字符80% similar UnverifiedLLM context windows have a fixed capacity limit such as 128K or 200K tokens73% similar Unverified不同大模型在上下文窗口大小方面存在显著差异，从8K到128K tokens不等73% similar Unverified短期工作记忆即上下文窗口通常为8K至128K tokens，长期记忆通常以向量数据库形式存储72% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/563319

API

curl https://kongchang.com/api/v1/knowledge/claims/563319

MCP

get_claim(id=563319)