Sparse FP4 Compression Suite of Qwen 3 models, compressed using sparsification and 4-bit floating point precision for low-resource deployment. cortecs/Qwen3-8B-NVFP4 5B • Updated Nov 27, 2025 • 179 cortecs/Qwen3-8B-NVFP4A16 5B • Updated Nov 27, 2025 • 36 cortecs/Qwen3-8B-clean-sparse-nvfp4a16 5B • Updated Nov 27, 2025 • 6 cortecs/Qwen3-8B-clean-sparse-finetuned-0.1-nvfp4a16 5B • Updated Nov 27, 2025 • 10
Sparse FP4 Compression Suite of Qwen 3 models, compressed using sparsification and 4-bit floating point precision for low-resource deployment. cortecs/Qwen3-8B-NVFP4 5B • Updated Nov 27, 2025 • 179 cortecs/Qwen3-8B-NVFP4A16 5B • Updated Nov 27, 2025 • 36 cortecs/Qwen3-8B-clean-sparse-nvfp4a16 5B • Updated Nov 27, 2025 • 6 cortecs/Qwen3-8B-clean-sparse-finetuned-0.1-nvfp4a16 5B • Updated Nov 27, 2025 • 10
