Unverified50% confidenceFactExact time
According to a report by MarkTechPost, LEANN achieves accuracy comparable to HNSW at 90% recall, with memory usage of 4 GB versus 188 GB.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/28/2026
First Seen
Valid until: 1/26/2027
Sources
Related Entities
Related Claims
UnverifiedAt a scale of 1 million vectors, PRISM achieves 99% recall and 15 milliseconds median latency on a 2GB c8g.medium; HNSW on a 4GB c8g.large is 392 milliseconds, with building taking about 21.7 hours and exhibiting memory thrashing.71% similarUnverifiedOn a machine with 2 GB of memory, first rendering a low-resolution proof to check the edges can reduce peak memory per file from 400 MB to 40 MB.69% similarUnverifiedConverting the 8-bit Ngram table to 4-bit can save approximately 100 GB, reducing the model size from approximately 475 GB to approximately 385 GB.69% similarUnverifiedFor 1 million tokens, the KV Cache alone can consume hundreds of GB of VRAM at FP16 precision, far exceeding the 80 GB capacity limit of a single A100/H100.69% similarVerifiedQ4_K_M uses mixed precision, storing some critical weights at 6-bit and the remainder at 4-bit, with an overall average of approximately 4.5-bit.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1105695API
curl https://kongchang.com/api/v1/knowledge/claims/1105695MCP
get_claim(id=1105695)