Unverified50% confidenceFactExact time
The BF16 weight files for Naive-N0.5-Flash are approximately 618GB, and the FP8 format version weights are approximately 315GB
1
Sources
50%
Confidence
Long-term
Relevance
9/28/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAccording to community-cited information, DeepSeek-V4.1-Flash has 552B backbone parameters, 196B Engram parameters, and safetensors weight files totaling approximately 350 GB.77% similarVerifiedA 35B model requires approximately 70GB of VRAM at FP16 precision, far exceeding the RTX 5090's 32GB capacity, so single-GPU deployment requires quantization.75% similarUnverifiedM3原始权重存储下限：BF16约854GB，8-bit约428GB，4-bit约214GB75% similarUnverifiedHunyuan V3 has open-sourced a BF16 version and also provides an FP8 quantized version, with the FP8 version being approximately 300 GB.75% 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.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/957119API
curl https://kongchang.com/api/v1/knowledge/claims/957119MCP
get_claim(id=957119)