LLMobile.news

Cutting edge on edge devices.

Hugging Face

4 updates on Hugging Face.

  1. Hugging Face's SmolLM3 is a 3B model with 128k context and two reasoning modes

    Hugging Face released a 3B model with a 128k context window, six languages and a switchable reasoning mode, along with the full training recipe.

  2. Google AI Edge Gallery runs Gemma 3 1B and Qwen2.5 offline on Android

    An experimental Google app downloads LiteRT models from Hugging Face, runs chat, image questions and prompt tests offline, and prints decode speed per reply.

  3. HuggingSnap describes what the iPhone camera sees with a 500M model on the phone

    Hugging Face released an iPhone app that runs SmolVLM2 at 500M parameters through MLX, describing camera scenes, photos and video with no cloud call.

  4. Hugging Face releases SmolLM at 135M, 360M and 1.7B parameters

    Three base models trained on the newly released SmolLM-Corpus, with published memory footprints from 109.78 MB to 3422.76 MB.