view post Post 5,071 Run DeepSeek V4.1-Flash-1017 locally! π³We made 1-bit retain ~88.2% accuracy while shrinking size from 508GB to 250GB (β52%).Run on a 128GB+ RAM device. V4.1 Flash 1017 is the strongest open model to dateGuide: https://unsloth.ai/docs/models/deepseek-v4.1-flashGGUF: unsloth/DeepSeek-V4.1-Flash-1017-GGUF See translation π₯ 15 15 β€οΈ 5 5 π€― 3 3 π 2 2 + Reply
deepseek-ai/DeepSeek-V4.1-Flash-1017 Image-Text-to-Text β’ 763B β’ Updated 1 day ago β’ 330k β’ β’ 5.47k