deepseek-ai/DeepSeek-V3.2-Speciale Text Generation β’ 685B β’ Updated Dec 1, 2025 β’ 31.7k β’ 629
SINQ: Sinkhorn-Normalized Quantization for Calibration-Free Low-Precision LLM Weights Paper β’ 2509.22944 β’ Published Sep 26, 2025 β’ 79
MaziyarPanahi/Qwen3-30B-A3B-Instruct-2507-GGUF Text Generation β’ 31B β’ Updated Nov 20, 2025 β’ 70.3k β’ 2