Expired60% confidenceFactTime unknown
DeepSeek V4 Flash's KV Cache VRAM has been reduced to 7% of the V3.2 version (a 13.7x reduction).
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
6/2/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 8/31/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedAfter compression, the DeepSeek V4 Flash model size was reduced from nearly 500 GB to 80.8 GB.77% 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.74% similarVerifiedDeepSeek V4 Flash has 284B total parameters, activates 13B per inference, and requires approximately 150GB of VRAM.73% similarUnverifiedDeepSeek-V4 Pro has 1.6T parameters with 49B activated per inference; the Flash version has 284B parameters with 13B activated.72% similarUnverifiedThe API call cost of DeepSeek V4 Flash is typically a fraction of that of the full version.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/36598API
curl https://kongchang.com/api/v1/knowledge/claims/36598MCP
get_claim(id=36598)