ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF Text Generation • 27B • Updated about 9 hours ago • 56.2k • 120
Model Compression with Exact Budget Constraints via Riemannian Manifolds Paper • 2605.00649 • Published May 7 • 2
GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling Paper • 2604.18556 • Published Apr 20 • 11
ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF Text Generation • 27B • Updated about 9 hours ago • 56.2k • 120
GSQ-RCO-GGUF Collection Non-uniform GGUF quantizations via GSQ + RCO: per-tensor mixed precision in standard GGUF form • 1 item • Updated 4 days ago
Model Compression with Exact Budget Constraints via Riemannian Manifolds Paper • 2605.00649 • Published May 7 • 2
GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling Paper • 2604.18556 • Published Apr 20 • 11
GSQ Collection GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling, https://huggingface.co/papers/2604.18556 • 10 items • Updated 10 days ago • 9
RCO Collection 11:04 AM RCO: Model Compression with Exact Budget Constraints via Riemannian Manifolds, https://huggingface.co/papers/2605.00649 • 1 item • Updated Jun 22