onwx 0.3.0

0.2.2: Qwen3.5 4B and llm-jp-4.1 8B thinking in the catalog; prefill fix for models whose layer 0 is attention

0.2.1: Qwen3.5 9B (int4, images; prefill on the NPU) in the catalog, settings text fix

0.2.0: context up to 262144 tokens, faster long prompts

Download size in GB (7.6 GB)

onwx 0.1.0: LLMs entirely on the AMD Ryzen AI NPU (XDNA2)

initial commit