[KongchangAI]
Unverified50% confidenceFactExact time

The entire FuseAMC model has about 0.2 million parameters, a model footprint of only a few megabytes, and about 3 MFLOPs of computation per frame.

1
Sources
50%
Confidence
Long-term
Relevance
11/5/2026
First Seen

Sources

Runs on CPU Too! FuseAMC: A New Model for Modulation Recognition Fusing Deep and Classical Methods

Related Entities

FuseAMCmodel

Related Claims

UnverifiedMeta的Llama 3.1 70B参数模型以FP16加载约需140GB，405B参数模型以FP16加载约需810GB，INT4量化后约202GB69% similarUnverifiedLLaMA-2 70B 总参数约 700 亿均匀分布于 80 层，每层约 8.75 亿参数，FP16 精度下单层约占 1.75GB 显存67% similar

Cite This Claim

Stable URI
https://kongchang.com/claim/1138038
API
curl https://kongchang.com/api/v1/knowledge/claims/1138038
MCP
get_claim(id=1138038)