Unverified50% confidenceFactExact time
ScopeGuard uses the all-MiniLM-L6-v2 model for local embeddings; the model has about 22 million parameters and can encode in milliseconds on a CPU.
1
Sources
50%
Confidence
Long-term
Relevance
10/18/2026
First Seen
Sources
Related Entities
Related Claims
Unverifiedall-MiniLM-L6-v2 is an open-source sentence vector model with 384 dimensions, a model size of approximately 80 MB, and can complete single-item encoding on a standard CPU with millisecond-level latency.75% similarUnverifiedSuch micro LLMs typically have parameter scales ranging from 1B to 7B, and can perform local inference of tens of tokens per second on mobile or wearable chips.66% similarUnverifiedTinyML模型几乎都是单一任务、固定功能的，通常只有几十KB到几MB大小，而Needle定位为具备通用能力的基础模型66% similarUnverifiedThe benchmark uses llama2.c locked to a specific commit, paired with TinyStories FP32 checkpoints (15M, 42M, 110M parameters); these are small models running on llama2.c rather than the full Llama 2.66% similarUnverified模型使用每个词256维可学习向量，参数总量约2560万，几乎全部集中在共享井表中65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1063379API
curl https://kongchang.com/api/v1/knowledge/claims/1063379MCP
get_claim(id=1063379)