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.
Qwen3.5-ANE-CoreMLQwen3.5-0.8B-Chat-CoreMLDolphin3.0-CoreMLQwen3.8-27B-coreml-q4FunctionGemma-270M-CoreML-Palettize8grio-qwen2.5-1.5b-instruct-coreml-stateful-int8coreml-Qwen2.5-0.5B-Instruct-4bitQwen3-0.6B-Chat-CoreMLMiniCPM5-1B-CoreML-4bitcoreml-SmolLM2-135M-Instruct-8bitcoreml-SmolLM2-360M-Instruct-4bitgrio-qwen2.5-0.5b-coreml-anyLM-seq512coreml-SmolLM2-135M-Instruct-4bitgrio-gemma-3-1b-coreml-anyLM-seq2048Qwen3-0.6B-CoreML-4bitQwen3.5-0.8B-coremlcoreml-Qwen2.5-3B-Instruct-4bitcoreml-SmolLM2-1.7B-Instruct-4bitcoreml-SmolLM2-1.7B-Instruct-8bitgrio-gemma-3-1b-coreml-anyLM-seq1024coreml-Qwen2.5-Coder-1.5B-Instruct-4bitgrio-qwen2.5-1.5b-coreml-anyLM-seq512coreml-Llama-3.2-1B-Instruct-4bitgrio-qwen2.5-0.5b-coreml-anyLM-seq2048grio-llama-3.2-1b-instruct-coreml-statefulcoreml-Llama-3.2-3B-Instruct-4bitcoreml-SmolLM2-360M-Instruct-8bitgrio-llama-3.2-1b-coreml-anyLM-seq512coreml-Qwen2.5-Coder-0.5B-Instruct-4bitLance-3B-Video-und-CoreML-palettized-4bit