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.
Sparse-Llama-3.1-8B-2of4-GGUFneuralmagic_-_SparseLlama-3-8B-pruned_50.2of4-ggufSparse-Llama-3.1-8B-2of4-GGUFllama2.c-stories42M-gsm8k-sparse-only-uncompressedSparseLLM_-_prosparse-llama-2-7b-ggufSparseLLM_-_prosparse-llama-2-13b-ggufZhMax_-_llama-2-7b-ebft-sparsegpt-outlier-wiki-block-outlier-ggufllama2.c-stories42M-gsm8k-sparse-only-compressedneuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-GGUFneuralmagic-SparseLlama-3-8B-pruned_50.2of4-GGUFprosparse-llama-2-7bSparseLlama-3-8B-pruned_50.2of4-GGUFSparse-Llama-3.1-8B-2of4-GGUFSparseGPT-pruned-Llama-2-7b-0.3-GGUFneuralmagic.Sparse-Llama-3.1-8B-2of4-GGUFneuralmagic.Sparse-Llama-3.1-8B-ultrachat_200k-2of4-GGUFprosparse-llama-2-7b-ggufprosparse-llama-2-13b-ggufSparse-Llama-3.1-8B-2of4SparseLlama-3-8B-pruned_50.2of4Llama-3.2-3B-Instruct-SparseGPT-GGUFSparse_llama-7Bprosparse-llama-2-13bSparse-Llama-3.1-8B-tldr-2of4-FP8-dynamicSparseLlama-3.1-8B-gsm8k-pruned.2of4-chnl_wts_per_tok_dyn_act_fp8-BitMSparseLLama-2-7b-ultrachat_200k-pruned_50.2of4Sparse-Llama-3.1-8B-gsm8k-2of4-FP8-dynamicSparse-Llama-3.1-8B-ultrachat_200k-2of4Sparse-Llama-3.1-8B-gsm8k-2of4-quantized.w4a16llama-7B-sparsetest-c4-25pct-128blksz