deepseek-v4.1POST

First NVFP4 build of DeepSeek V4.1 Flash 1017 lands on Hugging Face at ~430GB

Experts are losslessly transcoded from MXFP4 to NVFP4 at about 430GB, fitting on four DGX Sparks with roughly 80GB left for KV cache, with a two-Spark build reportedly in the works.

𝙒𝙞𝙡𝙘𝙤 𝘷𝘢𝘯 𝘽𝙤𝙭𝙩𝙚𝙡 ⚡🚀🧲🌞

@nuonrgArchived 10 days agoOriginally posted 2026.10.17

𝙒𝙞𝙡𝙘𝙤 𝘷𝘢𝘯 𝘽𝙤𝙭𝙩𝙚𝙡 ⚡🚀🧲🌞 @nuonrgOriginally posted 2026.10.17

Open original on X

First NVFP4 build of DeepSeek V4.1 Flash 1017 is already on Hugging Face: lossless MXFP4 to NVFP4 transcode of the experts, about 430GB. That fits on 4 DGX Sparks with roughly 80GB left for KV cache. A 2-Spark build is reportedly in the works. GLM-5.3 Flash finally has competition on my cluster. #AI #LocalAI #Deepseek https://huggingface.co/LibertAIDAI/DeepSeek-V4.1-Flash-1017-NVFP4

x.com/nuonrg/status/2111393037406359586Archived 2026.10.18 16:45