Swift developers can swap one import to access open-weight models on-device via MLX, llama.cpp or Core ML, or hosted providers, all with the same Foundation Models-style…
A preprint introduces user-side pseudo-anonymization that replaces PII with realistic surrogates, keeping real names, numbers, and details on your device while still letting…
Fly.io's persistent Linux sandbox VMs now route calls to Ollama Cloud models like kimi-k3 and glm-5.3 through an encrypted gateway that injects API keys without exposing them.…
arXiv preprint dated October 5 2026 presents the first systematic measurements of complete training runs for a 3B-parameter model on a mobile device, covering memory, time…
New @huggingface/kernels JavaScript library and 207 WebGPU kernels published on the Hub provide optimized, inspectable operations for browser-based local AI. Fleet crowdsources…
Transformers can now load and run GGUF files directly on Apple Silicon using ggml kernels, delivering near-llama.cpp performance while keeping the familiar Python and PyTorch…