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.
NVIDIA-Nemotron-Nano-9B-v2-4bitsG9v3-39A5B-4bits-mlxmarlin-2B-GPTQ-4BITSBaichuan2-13B-Chat-4bitsBaichuan2-7B-Chat-4bitsCodeFuse-CodeLlama-34B-4bitsCodeFuse-DeepSeek-33B-4bitsGLM-4.7-REAP-50-mixed-3-4-bitsDolphin3.0-R1-Mistral-24B-MLX-4bitsBlueLM-7B-Chat-4bitsPoro-34B-chat-4bits-mlxZGCM-1-7B-4bits-MLXFalcon3-Mamba-7B-Instruct-4bitsGemma-SEA-LION-v4.5-E2B-IT-4bitsLlama3-Taiwan-70B-Instruct-128K-AWQ-4bitsQwen2.5-Coder-14B-Instruct-MLX-4bitsautoj-13b-GPTQ-4bitsTinyMistral-248M-4bitsDolphin3.0-Mistral-24B-MLX-4bitsQwen2.5-Coder-7B-Instruct-MLX-4bitsStableBeluga-7BNVIDIA-Nemotron-Nano-9B-v2-4bits-mlx-4Bitstable-vicuna-13B-GPTQOpenAssistant-falcon-40B-4-bits-autogptqjais-13b-chat_bitsandbytes_4bitbuffer-baichuan2-13B-rag-4bitsQwen2.5-Coder-3B-Instruct-MLX-4bitsLlama-3.2-1B-Instruct-HadamardSpin-4bitsh2o-llama2-7b-4bitsllama-3-newborn-4bits