This is the 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 for a version that works on NPU.

Downloads last month
48
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including llmware/DeepSeek-R1-Distill-Qwen-7B-ov-int4