Unverified50% confidenceBenchmarkExact time
Under clearly weaker hardware conditions, CACTUS is still more than 28 times faster than LLM-Surgeon.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/14/2026
First Seen
Valid until: 1/12/2027
Sources
Related Entities
Related Claims
UnverifiedThe browser version is approximately 27 times slower than the native version, but theoretically can run on AMD and Intel graphics cards.59% similarUnverifiedCompared with the full-rank (no low-rank approximation) approach, VPU at dim=256 reduced 200 steps from 4249ms to 160ms, achieving a 26.44x speedup.58% similarUnverifiedIn CPU tests on an M2 MacBook Air, Redux achieved 38× real-time speed while Parakeet CPP achieved only 12×, a roughly 3× lead; however, on the Mac GPU the two are close (43× vs. 38/39×).57% similarUnverifiedIn the 30-token configuration, the approach is 8.8× faster than Program-of-Thought and 2.8× more energy-efficient.56% similarUnverified测试者用双4090（48GB显存）工作站运行20.7B稠密模型，每秒生成27.6个Token，仅比矮星略快，但参数量小10倍以上55% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1022898API
curl https://kongchang.com/api/v1/knowledge/claims/1022898MCP
get_claim(id=1022898)