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.
MiniMax-H3-Pruned-GGUFMinimax-H3-pruned-GGUFgemma-4-26B-A4B-it-qat-q4_0-heretic-japanese-pruned-GGUFgemma-4-26B-A4B-it-qat-japanese-pruned-GGUFNa0s_-_Llama-3.1-8b-Pruned-4-Layers-ggufCodestral-21B-Pruned-i1-GGUFMixtral-8x7B-v0.1-instruct-l2-norm-post-SFT-pruned-3-experts-GGUFLlama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0-i1-GGUFLlama-2-7b-pruned70-retrained-gsm8k-GGUFDeepSeek-V4-Flash-0731-Pruned-155B-A13B-GGUFMiniMax-H3-FL2VA-Pruned-IQ1-GGUFMuse-Glimmer-30B-pruned-GGUFneuralmagic_-_SparseLlama-3-8B-pruned_50.2of4-ggufOpenAI_GPT-OSS-120B_Pruned_REAP_58B-SafeTensors-i1-GGUFneuralmagic_-_Llama-2-7b-pruned50-retrained-ggufQwen3.6-35B-A3b-pruned-v2Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-2.0-i1-GGUFLlama-3.1-8b-Pruned-6-Layers-GGUFLlama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-2.0-GGUFNa0s_-_Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0-ggufgpt-oss-6.0b-specialized-all-pruned-moe-only-7-experts-i1-GGUFLlama-3.1-8b-Pruned-3-Layers-GGUFQwen3.6-35B-A3B-128E-Pruned-GGUFLlama-3.1-8b-Pruned-4-Layers-GGUFKimi-K2.5-BF16-Pruned-20B-i1-GGUFLlama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0-GGUFMiniMax-H3-Pruned-Ref-Delta-Fused-GGUFLlama-3.1-8b-Pruned-1-Layer-GGUFQwen3.8-19B-Pruned-GGUFNa0s_-_Mixtral-8x7B-v0.1-instruct-pruned-random-4-experts-gguf