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.
XLM-Roberta-Large-ViT-H-14__frozen_laion5b_s13b_b90kQwen3.8-27B-5bit-MLX-TextOnlyApertus-v1.5-8B-text-MLX-5bitXLM-Roberta-Base-ViT-B-32__laion5b_s13b_b90kQwen2.5-Coder-1-5B-Instruct-f16-q4_k_mMiLMMT-46-4B-v1.0-5bit-MLXMOSS-Transcribe-Diarize-0.9B-MLX-5bitKAT-Dev-MLX-5bitDeepSeek-OCR-2-5bitDeepSeek-OCR-5bitOrnith-1.5-35B-A3B-5bit-MLXApertus-v1.5-8B-MLX-5bitOrnith-1.5-35B-A3B-5bit-MLX-TextOnlyQwen3.8-27B-5bit-MLXolmoe-1b-7b-compacted-5bgranite-4.0-1b-speech-5bitRWKV-Gemma-5B-E2B-Preview-0.1DeepSeek-R1-Distill-Qwen-1-5B-f16-iq2_xxs-GGUFPaddleOCR-VL-1.5-5bitHunyuan-MT2-1.8B-5bit-MLXPaddleOCR-VL-5bitDeepSeek-R1-Distill-Qwen-1-5B-f16-iq3_xxs-GGUFNemotron-3.5-ASR-Streaming-0.6B-MLX-5bitdots.mocr-5bitcogalign-llava-ov-0_5bdots.ocr-5bitmicrosoft_Phi-3-medium-128k-instruct-2_5bpw_exl2failspy_Phi-3-medium-4k-instruct-abliterated-v3-3_5bpw_exl2failspy_Phi-3-mini-4k-geminified-6_5bpw_exl2failspy_Phi-3-medium-4k-instruct-abliterated-v3-2_5bpw_exl2
