Model Compression with Exact Budget Constraints via Riemannian Manifolds Paper • 2605.00649 • Published May 7 • 2
GSQ Collection GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling, https://huggingface.co/papers/2604.18556 • 10 items • Updated 9 days ago • 9
ISTA-DASLab/Qwen3.6-35B-A3B-2Bit-GSQ Image-Text-to-Text • 36B • Updated 17 days ago • 260 • 3
GSQ Collection GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling, https://huggingface.co/papers/2604.18556 • 10 items • Updated 9 days ago • 9
GSQ Collection GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling, https://huggingface.co/papers/2604.18556 • 10 items • Updated 9 days ago • 9