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.
Qwen2.5-Coder-1.5B-mobileQwen2.5-Coder-7B-mobileQwen2.5-Math-1.5B-mobileQwen2.5-1.5B-Instruct-mobile-int4Gemma-2-2B-IT-mobileTinyLlama-1.1B-Chat-mobile-int4SmolLM2-360M-Instruct-mobileLlama-3.2-3B-Instruct-Q5-mobileQwen2.5-1.5B-Instruct-Q5-mobileQwen2.5-0.5B-Instruct-Server-mobileTinyLlama-1.1B-Chat-Q5-mobileSmolLM2-1.7B-Instruct-mobileQwen2.5-1.5B-Instruct-Q8-mobileSmolLM2-135M-Instruct-mobileQwen3-Embedding-0.6B-Q8-mobileWhisper-Small-ASR-mobileEmbeddingGemma-300M-Q8-mobileMiniCPM5-1B-mobileMiniCPM5-1B-multilingual-mobileSmolLM2-1.7B-Instruct-Q5-mobilePhi-3.5-mini-Instruct-mobileQwen2.5-0.5B-Chinese-mobileGemma-2-2B-IT-Q5-mobileQwen3-Embedding-0.6B-mobilePhi-3.5-mini-instruct-Q5-mobileEmbeddingGemma-300M-mobile