Unverified50% confidenceFactExact time
DeepSeek-V3 总参数达 685B，以 Q4 量化后体积仍超过 400GB
1
Sources
50%
Confidence
Long-term
Relevance
10/7/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedDeepSeek R1 7B版本原始FP16精度约需14GB存储，量化后仅需4.7GB78% similarUnverifiedDeepSeek发布了V4的首个视觉版本权重，模型规模达到305B（约3050亿参数）77% similarUnverifiedDeepSeek V1时代每个增量token需要近400KB的KV缓存，V3.2降到48KB77% similarVerified以 GGUF Q4 量化为基准，7B 模型约需 4-6GB 显存，13B 约需 8-10GB，70B 需 40GB 以上或多 GPU 并行77% similarVerifiedQwen2.5:7B模型Q4量化后文件大小约为4GB76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/985470API
curl https://kongchang.com/api/v1/knowledge/claims/985470MCP
get_claim(id=985470)