Expired50% confidenceFactExact time
OpenAI's text-embedding-3 or the open-source BGE-M3 can generate dense vectors of 1536 dimensions or more
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/14/2026
First Seen
Valid until: 10/12/2026(expired)
Sources
AI Agent学习路线全拆解：从零基础到独立开发智能体
Related Claims
UnverifiedOpenAI's text-embedding-3-small outputs 1536-dimensional vectors, while BGE-large-zh outputs 1024-dimensional vectors.81% similarUnverifiedQwen 3.6 35B A3B is fully open-source, with weights available on Hugging Face at approximately 72 GB in size.63% similarUnverifiedLlama 3 8B has 32 layers, 8 KV heads (GQA architecture with 32 query heads), a head dimension of 128, and a KV cache of approximately 1.07 GB for a single sequence under FP16 with an 8192 context length.61% similarUnverifiedConnecting to agent frameworks such as Hermes or OpenCore requires at least 64K context, which 16GB VRAM cannot support; 24GB or more VRAM is recommended.61% similarUnverified千问3.8 27B是27.8B的稠密模型，支持图像和视频原生多模态输入，原生262K上下文60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/510668API
curl https://kongchang.com/api/v1/knowledge/claims/510668MCP
get_claim(id=510668)