GSQ Collection GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling, https://huggingface.co/papers/2604.18556 • 9 items • Updated May 25 • 9
deucebucket/Gemma-4-26B-A4B-it-Cerebellum-v6-GGUF Text Generation • 25B • Updated 23 days ago • 533 • 10