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.
Qwen3-VL-Embedding-2B-AWQ-4bitKimi-VL-A3B-Thinking-4bitbge-m3-mlx-4bitInternVL3_5-38B-AWQ-4bitOcten-Embedding-4B-MLX-4bitDeepSeek-OCR-4bitDeepSeek-OCR-2-4bitPhi-4-mini-instruct-bnb-4bitNemotron-3-Embed-1B-BF16-4bitjina-reranker-v3-4bit-mxfp4InternVL3_5-14B-AWQ-4bitInternVL3_5-8B-AWQ-4bitNemotron-3-Embed-8B-Community-MLX-4bitInternVL3-2B-4bitInternVL3-1B-4bitharrier-oss-v1-270m-MLX-4bitInternVL3-14B-4bitInternVL3-38B-4bitgemma-3-12b-it-backbone-4bit-mlxInternVL3-78B-4bitInternVL3-9B-4bitOcten-Embedding-4B-MLX-4bitQwen3-Embedding-4B-MLX-4bitllama-embed-nemotron-8b-mlx-4bitmirror-mlx-community-DeepSeek-OCR-4bitQwen3-Embedding-0.6B-MLX-4bitQwen3-Embedding-8B-MLX-4bitNemotron-3-Embed-1B-BF16-MLX-4bitbge-reranker-v2-m3-bnb-4bitvoyage-4-nano-mlx-4bit
