GSQ-RCO-GGUF Collection Non-uniform GGUF quantizations via GSQ + RCO: per-tensor mixed precision in standard GGUF form โข 3 items โข Updated 1 day ago โข 72
GSQ Collection GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling, https://huggingface.co/papers/2604.18556 โข 8 items โข Updated 1 day ago โข 16