Unverified50% confidenceBenchmarkExact time
From V1 to V4.1 Flash, the single-token cache was compressed from 389,000 bytes to 890 bytes, a total compression of 437 times.
1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAfter compression, the DeepSeek V4 Flash model size was reduced from nearly 500 GB to 80.8 GB.73% similarUnverifiedV4 Flash's cache size is only 7% of that of V3.2.71% similarUnverified以quality=75压缩一张569,826字节的JPEG图片后，文件缩小到376,630字节，压缩率为33%71% similarUnverifiedThe UD-Q8_K_XL quantized version of DeepSeek V4 Flash has a file size of 162 GB, uses MXFP4+BF16 mixed precision, and achieves completely lossless quality.71% similarVerifiedEven compressing the weights to 214GB using 4-bit quantization still far exceeds the capacity of a single 48GB GPU.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/900713API
curl https://kongchang.com/api/v1/knowledge/claims/900713MCP
get_claim(id=900713)