# Notices

## Model

The model artifacts derive from Qwen3.8-Flash-Next and Qwen3.8-Flash-Next-FP8 at the revisions named in the model card. They are distributed under the included Qwen Community License 1.0.

## Runtime

The required runtime is published separately at <https://github.com/ciru-ai/Qwen3.8-Flash-CIRU-STRIX-IU4>. It is based on llama.cpp and retains the MIT license. Included CIRU runtime changes incorporate or adapt MIT-licensed work from the llama.cpp community and AMD helper code whose source notices are preserved.

Runtime credit includes Qwen; ggml-org and llama.cpp contributors; Ryan Monsurate for Qwen experimental/MTP integration work adapted by CIRU; AMD's open-source ROCm ecosystem; and the contributors named in the runtime's `THIRD_PARTY_NOTICES.md`.

## Trademarks and affiliation

Qwen and AMD names and logos belong to their respective owners. CIRU is an independent community research project and is not sponsored or endorsed by Qwen or AMD.