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 ↗ · 2026-11-12T02:17:04.301031227ZazureFoundry/HuggingFace/microsoft-xtremedistil-l6-h384-uncased@5
`microsoft/xtremedistil-l6-h384-uncased` is a pre-trained language model available on the Hugging Face Hub. It's specifically designed for the `text-classification` task in the `transformers` library. If you want to learn more about the model's architecture, hyperparameters, limi
azureFoundry/azureml/ministral-3-3b-instruct-2512-cuda-gpu@2
This model is an optimized version of Ministral-3-3B-Instruct-2512 for local inference on CUDA GPUs. This optimized model is published here in ONNX format to run on CUDA-capable GPU devices, with the precision best suited to this target. # ONNX Models Here are some of the optimi
- Maximum output
- 2,048
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, toolCalling, visionInput
azureFoundry/azureml/ministral-3-3b-instruct-2512-generic-cpu@2
This model is an optimized version of Ministral-3-3B-Instruct-2512 for local inference on CPU and mobile devices. This optimized model is published here in ONNX format to run on CPU and mobile targets, with the precision best suited to this target. # ONNX Models Here are some of
- Maximum output
- 2,048
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, toolCalling, visionInput
azureFoundry/azureml/ministral-3-3b-instruct-2512-generic-gpu@2
This model is an optimized version of Ministral-3-3B-Instruct-2512 for local inference on WebGPU-capable devices. This optimized model is published here in ONNX format to run with the WebGPU execution provider, with the precision best suited to this target. # ONNX Models Here ar
- Maximum output
- 2,048
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, toolCalling, visionInput
azureFoundry/azureml/Mistral-7B-Instruct-v0-2-openvino-gpu@2
This model is an optimized version of Mistral-7B-Instruct-v0.2 to enable local inference on Intel GPUs. # Model Description - **Developed by:** Microsoft - **Model type:** ONNX - **License:** apache-2.0 - **Model Description:** This is a conversion of the Mistral-7B-Instruct-v0.
- Maximum output
- 2,048
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/Mistral-7B-Instruct-v0-2-openvino-npu@3
This model is an optimized version of Mistral-7B-Instruct-v0.2 to enable local inference on Intel NPUs. # Model Description - **Developed by:** Microsoft - **Model type:** ONNX - **License:** apache-2.0 - **Model Description:** This is a conversion of the Mistral-7B-Instruct-v0.
- Maximum output
- 2,048
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/Mistral-7B-Instruct-v0-2-vitis-npu@2
This model is an optimized version of Mistral-7B-Instruct-v0.2 to enable local inference on AMD NPUs. # Model Description - **Developed by:** Microsoft - **Model type:** ONNX - **License:** apache-2.0 - **Model Description:** This is a conversion of the Mistral-7B-Instruct-v0.2
- Maximum output
- 2,048
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/mistralai-Mistral-7B-Instruct-v0-2-cuda-gpu@2
This model is an optimized version of Mistral-7B-Instruct-v0.2 to enable local inference on CUDA GPUs. This model uses RTN quantization. # Model Description - **Developed by:** Microsoft - **Model type:** ONNX - **License:** apache-2.0 - **Model Description:** This is a conversi
- Maximum output
- 2,048
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/mistralai-Mistral-7B-Instruct-v0-2-generic-cpu@3
This model is an optimized version of Mistral-7B-Instruct-v0.2 to enable local inference on CPUs. This model uses RTN quantization. # Model Description - **Developed by:** Microsoft - **Model type:** apache-2.0 - **License:** MIT - **Model Description:** This is a conversion of
- Maximum output
- 2,048
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/mistralai-Mistral-7B-Instruct-v0-2-generic-gpu@2
This model is an optimized version of Mistral-7B-Instruct-v0.2 to enable local inference on GPUs. This model uses RTN quantization. # Model Description - **Developed by:** Microsoft - **Model type:** ONNX - **License:** apache-2.0 - **Model Description:** This is a conversion of
- Maximum output
- 2,048
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/mistralai-Mistral-7B-Instruct-v0-2-trtrtx-gpu@2
This model is an optimized version of Mistral-7B-Instruct-v0.2 to enable local inference on TensorRT-RTX GPUs. # Model Description - **Developed by:** Microsoft - **Model type:** ONNX - **License:** apache-2.0 - **Model Description:** This is a conversion of the Mistral-7B-Inst
- Maximum output
- 2,048
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/mistral-nemo-12b-instruct-cuda-gpu@1
This model is an optimized version of Mistral-Nemo-Instruct-2407 to enable local inference on CUDA GPUs. This model uses GPTQ quantization. # Model Description - **Developed by:** Microsoft - **Model type:** ONNX - **License:** apache-2.0 - **Model Description:** This is a conve
- Maximum output
- 2,048
- Input modalities
- text
- Output modalities
- text
- Capabilities
- toolCalling
azureFoundry/azureml/mistral-nemo-12b-instruct-generic-cpu@1
This model is an optimized version of Mistral-Nemo-Instruct-2407 to enable local inference on CPUs. This model uses GPTQ quantization. # Model Description - **Developed by:** Microsoft - **Model type:** ONNX - **License:** apache-2.0 - **Model Description:** This is a conversion
- Maximum output
- 2,048
- Input modalities
- text
- Output modalities
- text
- Capabilities
- toolCalling
azureFoundry/azureml/mistral-nemo-12b-instruct-generic-gpu@1
This model is an optimized version of Mistral-Nemo-Instruct-2407 to enable local inference on GPUs. This model uses GPTQ quantization. # Model Description - **Developed by:** Microsoft - **Model type:** ONNX - **License:** apache-2.0 - **Model Description:** This is a conversion
- Maximum output
- 2,048
- Input modalities
- text
- Output modalities
- text
- Capabilities
- toolCalling
azureFoundry/azureml-routers/model-router@2025-05-19
An affordable, efficient AI solution for diverse text and image tasks.
- Context window
- 1,048,576
- Maximum output
- 32,768
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, visionInput
azureFoundry/azureml-routers/model-router@2025-08-07
Model router is a deployable AI model that is trained to select the most suitable large language model (LLM) for a given prompt.
- Context window
- 1,048,576
- Maximum output
- 32,768
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, toolCalling, visionInput
azureFoundry/azureml-routers/model-router@2025-11-18
Model router is a deployable AI model that is trained to select the most suitable large language model (LLM) for a given prompt.
- Context window
- 1,048,576
- Maximum output
- 32,768
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, toolCalling, visionInput
cheaperInference/multilingual-e5-large
- Maximum output
- 512
- Output modalities
- embeddings
- Capabilities
- embeddings