models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
LongCat-Flash-Lite-Sparse-Uncensored-Heretic-Native-MTP-And-LSA-Preserved-GGUFLongCat-Flash-Lite-Sparse-Ultra-Uncensored-Heretic-Native-MTP-And-LSA-Preserved-GGUFSparse-Llama-3.1-8B-2of4-GGUFSparse-AST-BWMSparse-Llama-3.1-8B-2of4-GGUFqwen3-30b-a3b-thinking-opencode-sft-sparse-serveparityLongCat-Flash-Lite-SparseProSparse-MiniCPM-1B-sftyurts-python-code-gen-30-sparseneuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-GGUFneuralmagic-SparseLlama-3-8B-pruned_50.2of4-GGUFswiglu-10Bprosparse-llama-2-7bsparsetral-16x7B-v2BlockFFN-3B-SFT-EAGLESparse-Llama-3.1-8B-2of4-GGUFinclusionAI.Ring-mini-sparse-2.0-exp-GGUFbloom-560m_sparsegpt_0.5DSV2-Lite-DSA-Sparse-1250LongCat-Flash-Lite-Sparse-4bitRing-mini-sparse-2.0-expneuralmagic.Sparse-Llama-3.1-8B-2of4-GGUFgpt-neo-2.7B_sparsegpt_0.9bloom-560m_sparsegpt_0.7ReluLLaMA-7Bbloom-560m_sparsegpt_0.6neuralmagic.Sparse-Llama-3.1-8B-ultrachat_200k-2of4-GGUFbloom-560m_sparsegpt_0.8bloom-560m_sparsegpt_0.9PowerInfer.SparseQwen2-7B-GGUF
