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.
e5-mistral-7b-instruct-bnb-4bitall-MiniLM-L6-v2-4bitQwen3-Reranker-8B-bnb-4bitQwen3-Embedding-0.6B-4bit-DWQGiga-Embeddings-instruct-4bit-nf4Qwen3-Embedding-4B-4bit-DWQQwen3-VL-Embedding-2B-AWQ-4bitQwen3-Embedding-8B-4bit-DWQKimi-VL-A3B-Thinking-4bitall-MiniLM-L6-v2-4bitQwen3-Embedding-8B-4bit-MLXInternVL3_5-38B-AWQ-4bitinternlm2-chat-20b-4bitsqwen3-4b-text-embedding-4bitQwen3-VL-Embedding-2B-4bitDeepSeek-OCR-4bitDeepSeek-OCR-2-4bitinternlm-xcomposer2-vl-7b-4bitMiniCPM-o-4_5-4bitQwen3-Embedding-0.6B-MXL-4bitPhi-4-mini-instruct-bnb-4bitbge-small-en-v1.5-4bitQwen3-Embedding-0.6B-OptiQ-4bitQwen3-Embedding-8B-4bit-DWQQwen3-Embedding-4B-bnb-4bitQwen3.6-35B-A3B-bnb-4bitjina-reranker-v3-4bit-mxfp4InternVL3_5-14B-AWQ-4bitInternVL3_5-8B-AWQ-4bitQwen3-VL-Embedding-2B-mlx-4bit
