Microsoft

About Microsoft

Explore research at Microsoft, a site featuring the impact of research along with publications, products, downloads, and research careers.

Microsoft Research conducts fundamental science and technology research across a spectrum of research areas. With labs around the globe we pursue breakthroughs across the computing and AI stack to accelerate discovery across sciences and advance the frontiers of computing and AI to create new foundations for others to build upon.

Artificial intelligence | Search & information retrieval | Human language technologies | Human-computer interaction | Computer vision | Graphics & multimedia | Audio & acoustics

Medical, health & genomics | Economics | Social sciences | Technology for emerging markets | Ecology & environment

Website ↗Documentation ↗

Source ↗ · 2026-11-12T02:17:04.301031227Z

669 indexed models

669 matching models

DeepSeek-R1-Distill-Qwen-14B-openvino-gpu · azureml v2

azureFoundry/azureml/DeepSeek-R1-Distill-Qwen-14B-openvino-gpu@2

This model is an optimized version of DeepSeek-R1-Distill-Qwen-14B to enable local inference on Intel GPUs. # Model Description - **Developed by:** Microsoft - **Model type:** ONNX - **License:** MIT - **Model Description:** This is a conversion of the DeepSeek-R1-Distill-Qwen-1

Maximum output
2,048
Input modalities
text
Output modalities
text

deepseek-r1-distill-qwen-14b-qnn-npu · azureml v2

azureFoundry/azureml/deepseek-r1-distill-qwen-14b-qnn-npu@2

This model is an optimized version of DeepSeek-R1-Distill-Qwen-14B to enable local inference on QNN NPUs. This model uses QuaRot and GPTQ quantization. # Model Description - **Developed by:** Microsoft - **Model type:** ONNX - **License:** MIT - **Model Description:** This is a

Maximum output
2,048
Input modalities
text
Output modalities
text

deepseek-r1-distill-qwen-14b-trtrtx-gpu · azureml v2

azureFoundry/azureml/deepseek-r1-distill-qwen-14b-trtrtx-gpu@2

This model is an optimized version of deepseek-r1-distill-qwen-14b to enable local inference on TensorRT-RTX GPUs. # Model Description - **Developed by:** Microsoft - **Model type:** ONNX - **License:** MIT - **Model Description:** This is a conversion of the deepseek-r1-distill

Maximum output
2,048
Input modalities
text
Output modalities
text

deepseek-r1-distill-qwen-1.5b-cuda-gpu · azureml v4

azureFoundry/azureml/deepseek-r1-distill-qwen-1.5b-cuda-gpu@4

This model is an optimized version of DeepSeek-R1-Distill-Qwen-1.5B to enable local inference on CUDA GPUs. This model uses RTN quantization. # Model Description - **Developed by:** Microsoft - **Model type:** ONNX - **License:** MIT - **Model Description:** This is a conversion

Maximum output
2,048
Input modalities
text
Output modalities
text

deepseek-r1-distill-qwen-1.5b-generic-cpu · azureml v4

azureFoundry/azureml/deepseek-r1-distill-qwen-1.5b-generic-cpu@4

This model is an optimized version of DeepSeek-R1-Distill-Qwen-1.5B to enable local inference on CPUs. This model uses RTN quantization. # Model Description - **Developed by:** Microsoft - **Model type:** ONNX - **License:** MIT - **Model Description:** This is a conversion of t

Maximum output
2,048
Input modalities
text
Output modalities
text

deepseek-r1-distill-qwen-1.5b-generic-gpu · azureml v4

azureFoundry/azureml/deepseek-r1-distill-qwen-1.5b-generic-gpu@4

This model is an optimized version of DeepSeek-R1-Distill-Qwen-1.5B to enable local inference on GPUs. This model uses RTN quantization. # Model Description - **Developed by:** Microsoft - **Model type:** ONNX - **License:** MIT - **Model Description:** This is a conversion of t

Maximum output
2,048
Input modalities
text
Output modalities
text

DeepSeek-R1-Distill-Qwen-1.5B-openvino-gpu · azureml v2

azureFoundry/azureml/DeepSeek-R1-Distill-Qwen-1.5B-openvino-gpu@2

This model is an optimized version of DeepSeek-R1-Distill-Qwen-1.5B to enable local inference on Intel GPUs. # Model Description - **Developed by:** Microsoft - **Model type:** ONNX - **License:** MIT - **Model Description:** This is a conversion of the DeepSeek-R1-Distill-Qwen-

Maximum output
2,048
Input modalities
text
Output modalities
text

deepseek-r1-distill-qwen-1.5b-qnn-npu · azureml v2

azureFoundry/azureml/deepseek-r1-distill-qwen-1.5b-qnn-npu@2

This model is an optimized version of DeepSeek-R1-Distill-Qwen-1.5B to enable local inference on QNN NPUs. This model uses QuaRot and GPTQ quantization. # Model Description - **Developed by:** Microsoft - **Model type:** ONNX - **License:** MIT - **Model Description:** This is a

Maximum output
2,048
Input modalities
text
Output modalities
text

DeepSeek-R1-Distill-Qwen-1.5B-trtrtx-gpu · azureml v2

azureFoundry/azureml/DeepSeek-R1-Distill-Qwen-1.5B-trtrtx-gpu@2

This model is an optimized version of DeepSeek-R1-Distill-Qwen-1.5B to enable local inference on TensorRT-RTX GPUs. # Model Description - **Developed by:** Microsoft - **Model type:** ONNX - **License:** MIT - **Model Description:** This is a conversion of the DeepSeek-R1-Distil

Maximum output
2,048
Input modalities
text
Output modalities
text

deepseek-r1-distill-qwen-7b-cuda-gpu · azureml v4

azureFoundry/azureml/deepseek-r1-distill-qwen-7b-cuda-gpu@4

This model is an optimized version of DeepSeek-R1-Distill-Qwen-7B to enable local inference on CUDA GPUs. This model uses RTN quantization. # Model Description - **Developed by:** Microsoft - **Model type:** ONNX - **License:** MIT - **Model Description:** This is a conversion o

Maximum output
2,048
Input modalities
text
Output modalities
text

deepseek-r1-distill-qwen-7b-generic-cpu · azureml v4

azureFoundry/azureml/deepseek-r1-distill-qwen-7b-generic-cpu@4

This model is an optimized version of DeepSeek-R1-Distill-Qwen-7B to enable local inference on CPUs. This model uses RTN quantization. # Model Description - **Developed by:** Microsoft - **Model type:** ONNX - **License:** MIT - **Model Description:** This is a conversion of the

Maximum output
2,048
Input modalities
text
Output modalities
text

deepseek-r1-distill-qwen-7b-generic-gpu · azureml v4

azureFoundry/azureml/deepseek-r1-distill-qwen-7b-generic-gpu@4

This model is an optimized version of DeepSeek-R1-Distill-Qwen-7B to enable local inference on GPUs. This model uses RTN quantization. # Model Description - **Developed by:** Microsoft - **Model type:** ONNX - **License:** MIT - **Model Description:** This is a conversion of the

Maximum output
2,048
Input modalities
text
Output modalities
text

DeepSeek-R1-Distill-Qwen-7B-openvino-gpu · azureml v2

azureFoundry/azureml/DeepSeek-R1-Distill-Qwen-7B-openvino-gpu@2

This model is an optimized version of DeepSeek-R1-Distill-Qwen-7B to enable local inference on Intel GPUs. # Model Description - **Developed by:** Microsoft - **Model type:** ONNX - **License:** MIT - **Model Description:** This is a conversion of the DeepSeek-R1-Distill-Qwen-7B

Maximum output
2,048
Input modalities
text
Output modalities
text

DeepSeek-R1-Distill-Qwen-7B-openvino-npu · azureml v4

azureFoundry/azureml/DeepSeek-R1-Distill-Qwen-7B-openvino-npu@4

This model is an optimized version of DeepSeek-R1-Distill-Qwen-7B to enable local inference on Intel NPUs. # Model Description - **Developed by:** Microsoft - **Model type:** ONNX - **License:** MIT - **Model Description:** This is a conversion of the DeepSeek-R1-Distill-Qwen-7B

Maximum output
2,048
Input modalities
text
Output modalities
text

deepseek-r1-distill-qwen-7b-qnn-npu · azureml v2

azureFoundry/azureml/deepseek-r1-distill-qwen-7b-qnn-npu@2

This model is an optimized version of DeepSeek-R1-Distill-Qwen-7B to enable local inference on QNN NPUs. This model uses QuaRot and GPTQ quantization. # Model Description - **Developed by:** Microsoft - **Model type:** ONNX - **License:** MIT - **Model Description:** This is a c

Maximum output
2,048
Input modalities
text
Output modalities
text

DeepSeek-R1-Distill-Qwen-7B-trtrtx-gpu · azureml v2

azureFoundry/azureml/DeepSeek-R1-Distill-Qwen-7B-trtrtx-gpu@2

This model is an optimized version of DeepSeek-R1-Distill-Qwen-7B to enable local inference on TensorRT-RTX GPUs. # Model Description - **Developed by:** Microsoft - **Model type:** ONNX - **License:** MIT - **Model Description:** This is a conversion of the DeepSeek-R1-Distill-

Maximum output
2,048
Input modalities
text
Output modalities
text

DeepSeek-R1-Distill-Qwen-7B-vitis-npu · azureml v2

azureFoundry/azureml/DeepSeek-R1-Distill-Qwen-7B-vitis-npu@2

This model is an optimized version of DeepSeek-R1-Distill-Qwen-7B to enable local inference on AMD NPUs. # Model Description - **Developed by:** Microsoft - **Model type:** ONNX - **License:** MIT - **Model Description:** This is a conversion of the DeepSeek-R1-Distill-Qwen-7B f

Maximum output
2,048
Input modalities
text
Output modalities
text

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace