Open source
36 updates on Open source.
ClawMobile tries system commands before screen taps and finishes all six test tasks
An agent runtime that runs on the phone itself routes tasks to ADB commands before UI taps, and the authors report 100 percent completion on six tasks.
Apple ships Python bindings for the on-device Foundation Models framework
The apple-fm-sdk package calls the on-device Apple Intelligence model from Python on macOS 26, for scripting and batch evaluation outside Swift.
Show HN: Off Grid runs text, image, vision and speech models offline on phones
An MIT-licensed Android and iOS app bundles llama.cpp, Stable Diffusion and Whisper for offline use. The Show HN thread reached 124 points and 66 comments.
ExecuTorch 1.0 reaches general availability for on-device PyTorch models
The PyTorch edge runtime promotes Core ML, Qualcomm Hexagon, Arm Ethos-U, Vulkan and XNNPACK backends to production status.
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.
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.
Flower Intelligence runs models on device, with remote handoff off by default
Flower Labs released a preview library that runs Llama 3.2 and SmolLM2 locally via WebLLM or MLX Swift, and calls its remote service only if an app enables it.
Alibaba MNN runs 4-bit LLMs on phone CPUs and GPUs, with a multimodal Android app
MNN-LLM converts PyTorch checkpoints into a 4-bit MNN format for phones, and Alibaba reports prefill 8.6 times faster than llama.cpp on an Android CPU.
Hugging Face trains SmolLM2 at 135M, 360M and 1.7B on up to 11T tokens
Hugging Face released SmolLM2 in three sizes trained on up to 11 trillion tokens, with 4-bit builds from 118 MB for on-device runtimes.
AMD trains its first small language model, AMD-Llama-135M, on MI250 accelerators
AMD trained a 135M model from scratch on Instinct MI250 accelerators and reports up to 3.88x faster CodeLlama-7b inference when it drafts tokens.
CoMiGS splits on-device fine-tuning into shared generalists and private specialists
EPFL researchers split LoRA adapters into shared generalists and device-local specialists, and report 47.19 test perplexity against 54.38 for training alone.
MobiLlama is a fully transparent 0.5B model that runs in 770 MB on a phone
MBZUAI published a 0.5B model that shares one feed-forward block across all layers and reports 7.02 tok/s in 770 MB on a Snapdragon 685 phone.