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

CxrReportGen · azureml-ai-frontiers v1

azureFoundry/azureml-ai-frontiers/CxrReportGen@1

Grounded chest X-ray report generation model that produces radiology findings with bounding box annotations

Input modalities
image, text
Output modalities
text
Capabilities
multimodal, visionInput

CXRReportGen Premium · azureml-ai-frontiers-p v1

azureFoundry/azureml-ai-frontiers-p/CxrReportGen-Premium@1

The CXRReportGen Premium model is built on Qwen2.5-VL-7B-Instruct and is designed to help applications interpret complex chest X-ray imaging studies and generate radiology-style findings and impression.

Input modalities
image, text
Output modalities
text
Capabilities
multimodal, visionInput

CXRReportGen Premium · azureml-ai-frontiers-p v2

azureFoundry/azureml-ai-frontiers-p/CxrReportGen-Premium@2

The CXRReportGen Premium model is designed to help applications interpret complex chest X-ray imaging studies and generate radiology-style findings and impression.

Input modalities
image, text
Output modalities
text
Capabilities
multimodal, visionInput

Decision-1

vercelAIGatewayCatalog/microsoft/microsoft-decision-1

Microsoft Decision-1 is a text decision model from Microsoft AI for classification, routing, and evaluation. It answers yes/no questions, selects among predefined options, and scores inputs against custom criteria, returning calibrated probabilities and confidence values. With su

Context window
32,768
Input modalities
text
Output modalities
text
Capabilities
decision

Inference prices

DeepSeek-R1-Distilled-NPU-Optimized · azureml v1

azureFoundry/azureml/DeepSeek-R1-Distilled-NPU-Optimized@1

*Learn more: \[[original model announcement](https://github.com/deepseek-ai/DeepSeek-R1/tree/main)\]* DeepSeek-R1-Distilled-NPU-Optimized is a downloadable package of DeepSeek-R1-Distilled-Qwen-1.5B that is specifically optimized for the Neural Processing Unit (NPU). NPU optimiz

Input modalities
text
Output modalities
text

DeepSeek-R1-Distilled-NPU-Optimized · azureml v2

azureFoundry/azureml/DeepSeek-R1-Distilled-NPU-Optimized@2

*Learn more: \[[original model announcement](https://github.com/deepseek-ai/DeepSeek-R1/tree/main)\]* DeepSeek-R1-Distilled-NPU-Optimized is a downloadable package of DeepSeek-R1-Distilled-Qwen-1.5B that is specifically optimized for the Neural Processing Unit (NPU). NPU optimiz

Input modalities
text
Output modalities
text

DeepSeek-R1-Distilled-NPU-Optimized · azureml v3

azureFoundry/azureml/DeepSeek-R1-Distilled-NPU-Optimized@3

*Learn more: \[[original model announcement](https://github.com/deepseek-ai/DeepSeek-R1/tree/main)\]* DeepSeek-R1-Distilled-NPU-Optimized is a downloadable package of DeepSeek-R1-Distilled-Qwen-1.5B that is specifically optimized for the Neural Processing Unit (NPU). NPU optimiz

Input modalities
text
Output modalities
text

DeepSeek-R1-Distilled-NPU-Optimized · azureml v4

azureFoundry/azureml/DeepSeek-R1-Distilled-NPU-Optimized@4

*Learn more: \[[original model announcement](https://github.com/deepseek-ai/DeepSeek-R1/tree/main)\]* DeepSeek-R1-Distilled-NPU-Optimized is a downloadable package of DeepSeek-R1-Distilled-Qwen-1.5B that is specifically optimized for the Neural Processing Unit (NPU). NPU optimiz

Input modalities
text
Output modalities
text

DeepSeek-R1-Distilled-NPU-Optimized · azureml v5

azureFoundry/azureml/DeepSeek-R1-Distilled-NPU-Optimized@5

*Learn more: \[[original model announcement](https://github.com/deepseek-ai/DeepSeek-R1/tree/main)\]* DeepSeek-R1-Distilled-NPU-Optimized is a downloadable package of DeepSeek-R1-Distilled-Qwen-1.5B that is specifically optimized for the Neural Processing Unit (NPU). NPU optimiz

Input modalities
text
Output modalities
text

DeepSeek-R1-Distilled-NPU-Optimized · azureml v6

azureFoundry/azureml/DeepSeek-R1-Distilled-NPU-Optimized@6

*Learn more: \[[original model announcement](https://github.com/deepseek-ai/DeepSeek-R1/tree/main)\]* DeepSeek-R1-Distilled-NPU-Optimized is a downloadable package of DeepSeek-R1-Distilled-Qwen-1.5B that is specifically optimized for the Neural Processing Unit (NPU). NPU optimiz

Input modalities
text
Output modalities
text

DeepSeek-R1-Distilled-NPU-Optimized · azureml v7

azureFoundry/azureml/DeepSeek-R1-Distilled-NPU-Optimized@7

*Learn more: \[[original model announcement](https://github.com/deepseek-ai/DeepSeek-R1/tree/main)\]* DeepSeek-R1-Distilled-NPU-Optimized is a downloadable package of DeepSeek-R1-Distilled-Qwen-1.5B that is specifically optimized for the Neural Processing Unit (NPU). NPU optimiz

Input modalities
text
Output modalities
text

DeepSeek-R1-Distilled-NPU-Optimized · azureml v8

azureFoundry/azureml/DeepSeek-R1-Distilled-NPU-Optimized@8

*Learn more: \[[original model announcement](https://github.com/deepseek-ai/DeepSeek-R1/tree/main)\]* DeepSeek-R1-Distilled-NPU-Optimized is a downloadable package of DeepSeek-R1-Distilled-Qwen-1.5B that is specifically optimized for the Neural Processing Unit (NPU). NPU optimiz

Input modalities
text
Output modalities
text
Capabilities
reasoning

deepseek-r1-distill-llama-8b-cuda-gpu · azureml v4

azureFoundry/azureml/deepseek-r1-distill-llama-8b-cuda-gpu@4

This model is an optimized version of DeepSeek-R1-Distill-Llama-8B 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-llama-8b-generic-cpu · azureml v4

azureFoundry/azureml/deepseek-r1-distill-llama-8b-generic-cpu@4

This model is an optimized version of DeepSeek-R1-Distill-Llama-8B 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 th

Maximum output
2,048
Input modalities
text
Output modalities
text

deepseek-r1-distill-llama-8b-generic-gpu · azureml v4

azureFoundry/azureml/deepseek-r1-distill-llama-8b-generic-gpu@4

This model is an optimized version of DeepSeek-R1-Distill-Llama-8B 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 th

Maximum output
2,048
Input modalities
text
Output modalities
text

deepseek-r1-distill-qwen-14b-cuda-gpu · azureml v4

azureFoundry/azureml/deepseek-r1-distill-qwen-14b-cuda-gpu@4

This model is an optimized version of DeepSeek-R1-Distill-Qwen-14B 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-14b-generic-cpu · azureml v4

azureFoundry/azureml/deepseek-r1-distill-qwen-14b-generic-cpu@4

This model is an optimized version of DeepSeek-R1-Distill-Qwen-14B 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 th

Maximum output
2,048
Input modalities
text
Output modalities
text

deepseek-r1-distill-qwen-14b-generic-gpu · azureml v4

azureFoundry/azureml/deepseek-r1-distill-qwen-14b-generic-gpu@4

This model is an optimized version of DeepSeek-R1-Distill-Qwen-14B 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 th

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