Unverified50% confidenceFactExact time
OpenAI's text-embedding-3-large returns 3072-dimensional vectors by default, while pgvector's HNSW can index halfvec up to 4000 dimensions.
1
Sources
50%
Confidence
Long-term
Relevance
10/14/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedOfficial reports indicate that trimming text-embedding-3-large from 3072 dimensions to 256 dimensions results in only approximately 2–3% loss in retrieval accuracy on the MTEB benchmark.66% similarUnverifiedOn M4 Max, the text route using Omni 3B + TTS 1.7B (4.61 GB) has a median full-turn latency of 4.27 seconds, with a peak process RSS of 3.86 GiB.63% similarUnverifiedThe most advanced HBM3e memory bandwidth is approximately 4.8 TB/s, yet GPU compute utilization during inference often reaches only 30%–60%.60% similarUnverified自回归解码在批大小为1时算术强度约等于隐藏层维度（通常4096至16384），而现代GPU峰值算术强度往往超过200，导致解码处于内存带宽受限状态59% similarUnverifiedEmbeddingGemma 2's 740M parameters are divided into a text component of 270M (backbone 130M, embedding layer 140M), a vision encoder of 170M, and an audio encoder of 300M, with all three encoders loadable on demand.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1029341API
curl https://kongchang.com/api/v1/knowledge/claims/1029341MCP
get_claim(id=1029341)