models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
Qwen2.5-Coder-7B-Instruct-onnx-ryzenai-npuQwen2.5-7B-Instruct-onnx-ryzenai-npuQwen2.5-3B-Instruct-onnx-ryzenai-npuQwen2.5-Coder-1.5B-Instruct-onnx-ryzenai-npuLlama-3.2-1B-Instruct-onnx-ryzenai-npuLlama-3.1-8B-onnx-ryzenai-npuQwen3-8B_rai_1.8.0_npu_16Kgpt-oss-20B_eager_rai_1.8.0_npu_16KMeta-Llama-3.1-8B-Instruct-onnx-ryzenai-npuQwen2-1.5B-onnx-ryzenai-npuQwen-2.5_1.5B_Instruct-onnx-ryzenai-npuLlama-3.2-1B-onnx-ryzenai-npuGemma-3-4b_rai_1.8.0_npu_16Kgpt-oss-20b_rai_1.7.1_npu_4KLlama-3.2-1B-Instruct_rai_1.8.0_npu_4KQwen2.5-Coder-7B-Instruct_rai_1.7.1_npu_16KQwen3-4B_rai_1.8.0_npu_4KQwen3-VL-4B-Instruct_rai_1.8.0_npu_16Kembeddinggemma-300m_npu_rai_1.8.0_npu_4KLlama-2-7b-chat-hf-onnx-ryzenai-npuQwen2.5-Coder-7B-Instruct_rai_1.8.0_npu_16KQwen2.5-0.5B-Instruct_rai_1.8.0_npu_4KMistral-7B-Instruct-v0.3_rai_1.8.0_npu_4KMeta-Llama-3-8B-onnx-ryzenai-npuQwen1.5-7B-Chat-onnx-ryzenai-npuLlama-3.2-1B-Instruct_rai_1.8.0_npu_16KMistral-7B-Instruct-v0.3_rai_1.8.0_npu_16KQwen2-7B-onnx-ryzenai-npuLlama-3.2-3B-Instruct_rai_1.8.0_npu_4KQwen3-1.7B_rai_1.8.0_npu_4K