Hy-MT2 Jetson runtimes

Verified model-weight-free Docker load archives for AGX Orin (BF16) and AGX Thor (BF16 and FP8), published for the Hy-MT2 AI Pod installer v0.1.16. The runtimes use CUDA libraries mounted from the Jetson host. Model weights are downloaded separately from the upstream Tencent repositories.

See runtimes.json for archive sizes, SHA-256 hashes and image identities.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support