atomic.chat
@atomic_chat_hq
Local AI chat and Inference Engine. Enhanced by TurboQuant. Team: @gladkos @skinbagwbones @AlexFromAtomic @danyurkin @quantizedden
Joined March 2026
65 Following 17.2K Followers
Run DeepSeek V4.1 Flash NVFP4 locally đŗ
We made an NVFP4 build of DeepSeek's v4.1 flash model with @NVIDIAAI's ModelOpt recipe, every routed expert re-encoded bit-exactly for Blackwell's FP4 tensor cores and measured on 4x B200
NVFP4 build đ
Show more
đ Introducing DeepSeek-V4.1-Flash: smarter, faster, more efficient.
đš Introducing the smallest model in our new architecture family, with native visual understanding.
đš Designed for greater capability, faster inference, higher throughput, and scaling to larger models.
1/6
Show more
