Unverified50% confidenceFactExact time
GPT-3 reached a parameter scale of hundreds of billions (175 billion parameters) and demonstrated few-shot and zero-shot capabilities.
1
Sources
50%
Confidence
Long-term
Relevance
9/25/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe mini GPT model has a final parameter count of 13,693,824, which falls within the target range of 10–30 million.77% similarUnverifiedBERT的参数规模为3.4亿，GPT-3的参数规模为1750亿76% similarUnverified以GPT-3的1750亿参数为例，大约2/3的参数分布在FFN层中，1/3在注意力层中75% similarUnverifiedFull-parameter fine-tuning typically requires GPU memory 3–5 times the model's parameter count.68% similarUnverifiedA 70B-parameter model requires approximately 35–40GB of VRAM after Q4 quantization, which a single T4 cannot handle, but dual T4s can basically satisfy.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/949715API
curl https://kongchang.com/api/v1/knowledge/claims/949715MCP
get_claim(id=949715)