Today NVIDIA releases Alpamayo 2 Edge! I work for Embedl and we have already released an optimized version of the model that is more than 10x faster than pytorch when run on edge hardware like AGX Thor!
It's a collection of 1000+ models optimized to run fast on different edge devices like NVIDIA Orin Nano Super, AGX Thor, AGX Orin, Orin NX and RTX GPUs.
You can run the models directly on real edge devices through our free device farm, with detailed profiling and results! (As well as on your own device)
π£ HF Viewer now supports Hugging Face login! π€
β‘ Generate visualizations for all your models at once!
π Feature your models in the community showcase and set up your own profile/org collection page on hfviewer!
βοΈ Write your own model articles on hfviewer in the same novel interactive style as our "Gemma 4 family" article - with linking between the graph nodes and article text!
π We are also now rolling out support for tensor shapes, FLOPs and param counts per layer! :)
Thanks for all your positive feedback and suggestions! β€οΈ