DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models Paper β’ 2512.02556 β’ Published Dec 2, 2025 β’ 253
deepseek-ai/DeepSeek-V3.2-Exp Text Generation β’ 685B β’ Updated Nov 18, 2025 β’ 63.6k β’ β’ 944
Running on Zero Featured 101 PawMatchAI πΎ 101 Smart Dog Breed Detection, Comparison, and Matching Tool
view post Post 6634 Run DeepSeek-V3.1 locally on 170GB RAM with Dynamic 1-bit GGUFs!πGGUFs: unsloth/DeepSeek-V3.1-GGUFThe 715GB model gets reduced to 170GB (-80% size) by smartly quantizing layers.The 1-bit GGUF passes all our code tests & we fixed the chat template for llama.cpp supported backends.Guide: https://docs.unsloth.ai/basics/deepseek-v3.1 See translation β€οΈ 19 19 π₯ 9 9 π 5 5 + Reply