---
license: apache-2.0
---
This is the [Deepseek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) model, convert to OpenVINO with INT4 weight compression. This model is optimized for CPU and GPU. See [llmware/DeepSeek-R1-Distill-Qwen-7B-ov-int4-npu](https://huggingface.co/llmware/DeepSeek-R1-Distill-Qwen-7B-ov-int4-npu) for a version that works on NPU.