Unverified50% confidenceFactExact time
GFLOPs is a commonly used unit for measuring the computational cost of neural network inference, and 0.18 GFLOPs means a single frame requires only about 180 million floating-point operations.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe FilterFusion network itself has a computational cost of 0.18 GFLOPs.64% similarUnverifiedGLM-5.2 采用 IndexShare 技术，每四个稀疏注意力层复用同一个索引器，在 1M 上下文长度下将每 token 的 FLOPs 降低了 2.9 倍62% similarUnverified每个中间推理token与输出token消耗等量的GPU算力，Extra High档位单次请求FLOPs可能是普通生成模式的数十倍60% similarUnverifiedThe GLM-OCR model has 0.9B (900 million) parameters.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1046690API
curl https://kongchang.com/api/v1/knowledge/claims/1046690MCP
get_claim(id=1046690)