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

Phi-3-mini-128k-instruct · azureml v9

azureFoundry/azureml/Phi-3-mini-128k-instruct@9

## Model Summary The Phi-3-Mini-128K-Instruct is a 3.8 billion-parameter, lightweight, state-of-the-art open model trained using the Phi-3 datasets. This dataset includes both synthetic data and filtered publicly available website data, with an emphasis on high-quality and reaso

Input modalities
text
Output modalities
text

Phi-3-mini-128k-instruct-cuda-gpu · azureml v2

azureFoundry/azureml/Phi-3-mini-128k-instruct-cuda-gpu@2

This model is an optimized version of Phi-3-Mini-128K-Instruct 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 of t

Maximum output
2,048
Input modalities
text
Output modalities
text

Phi-3-mini-128k-instruct-generic-cpu · azureml v3

azureFoundry/azureml/Phi-3-mini-128k-instruct-generic-cpu@3

This model is an optimized version of Phi-3-Mini-128K-Instruct 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 Ph

Maximum output
2,048
Input modalities
text
Output modalities
text

Phi-3-mini-128k-instruct-generic-gpu · azureml v2

azureFoundry/azureml/Phi-3-mini-128k-instruct-generic-gpu@2

This model is an optimized version of Phi-3-Mini-128K-Instruct 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 Ph

Maximum output
2,048
Input modalities
text
Output modalities
text

Phi-3-mini-128k-instruct-openvino-gpu · azureml v2

azureFoundry/azureml/Phi-3-mini-128k-instruct-openvino-gpu@2

This model is an optimized version of Phi-3-Mini-128K-Instruct 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 Phi-3-Mini-128K-Instruct for l

Maximum output
2,048
Input modalities
text
Output modalities
text

phi-3-mini-128k-instruct-qnn-npu · azureml v4

azureFoundry/azureml/phi-3-mini-128k-instruct-qnn-npu@4

This model is an optimized version of phi-3-mini-128k-instruct to enable local inference on QNN NPUs. # Model Description - **Developed by:** Microsoft - **Model type:** ONNX - **License:** MIT - **Model Description:** This is a conversion of the phi-3-mini-128k-instruct for loc

Maximum output
2,048
Input modalities
text
Output modalities
text

phi-3-mini-128k-instruct-trtrtx-gpu · azureml v2

azureFoundry/azureml/phi-3-mini-128k-instruct-trtrtx-gpu@2

This model is an optimized version of phi-3-mini-128k-instruct 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 phi-3-mini-128k-instruc

Maximum output
2,048
Input modalities
text
Output modalities
text

phi-3-mini-128k-instruct-vitis-npu · azureml v2

azureFoundry/azureml/phi-3-mini-128k-instruct-vitis-npu@2

This model is an optimized version of Phi-3-mini-128k-instruct to enable local inference on AMD NPUs. 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

Phi-3-mini-4k-instruct · azureml v4

azureFoundry/azureml/Phi-3-mini-4k-instruct@4

## Model Details Phi-3 Mini-4K-Instruct is a 3.8B parameters, lightweight, state-of-the-art open model built upon datasets used for Phi-2 - synthetic data and filtered websites - with a focus on very high-quality, reasoning dense data. The model belongs to the Phi-3 model family

Input modalities
text
Output modalities
text

Phi-3-mini-4k-instruct · azureml v5

azureFoundry/azureml/Phi-3-mini-4k-instruct@5

## Model Details Phi-3 Mini-4K-Instruct is a 3.8B parameters, lightweight, state-of-the-art open model built upon datasets used for Phi-2 - synthetic data and filtered websites - with a focus on very high-quality, reasoning dense data. The model belongs to the Phi-3 model family

Input modalities
text
Output modalities
text

Phi-3-mini-4k-instruct · azureml v6

azureFoundry/azureml/Phi-3-mini-4k-instruct@6

## Model Details Phi-3 Mini-4K-Instruct is a 3.8B parameters, lightweight, state-of-the-art open model built upon datasets used for Phi-2 - synthetic data and filtered websites - with a focus on very high-quality, reasoning dense data. The model belongs to the Phi-3 model family

Input modalities
text
Output modalities
text

Phi-3-mini-4k-instruct · azureml v7

azureFoundry/azureml/Phi-3-mini-4k-instruct@7

## Model Details Phi-3 Mini-4K-Instruct is a 3.8B parameters, lightweight, state-of-the-art open model built upon datasets used for Phi-2 - synthetic data and filtered websites - with a focus on very high-quality, reasoning dense data. The model belongs to the Phi-3 model family

Input modalities
text
Output modalities
text

Phi-3-mini-4k-instruct · azureml v8

azureFoundry/azureml/Phi-3-mini-4k-instruct@8

## Model Details Phi-3 Mini-4K-Instruct is a 3.8B parameters, lightweight, state-of-the-art open model built upon datasets used for Phi-2 - synthetic data and filtered websites - with a focus on very high-quality, reasoning dense data. The model belongs to the Phi-3 model family

Input modalities
text
Output modalities
text

Phi-3-mini-4k-instruct · azureml v9

azureFoundry/azureml/Phi-3-mini-4k-instruct@9

## Model Summary The Phi-3-Mini-4K-Instruct is a 3.8B parameters, lightweight, state-of-the-art open model trained with the Phi-3 datasets that includes both synthetic data and the filtered publicly available websites data with a focus on high-quality and reasoning dense propert

Input modalities
text
Output modalities
text

Phi-3-mini-4k-instruct-cuda-gpu · azureml v2

azureFoundry/azureml/Phi-3-mini-4k-instruct-cuda-gpu@2

This model is an optimized version of Phi-3-Mini-4K-Instruct 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 of the

Maximum output
2,048
Input modalities
text
Output modalities
text

Phi-3-mini-4k-instruct-generic-cpu · azureml v3

azureFoundry/azureml/Phi-3-mini-4k-instruct-generic-cpu@3

This model is an optimized version of Phi-3-Mini-4K-Instruct 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 Phi-

Maximum output
2,048
Input modalities
text
Output modalities
text

Phi-3-mini-4k-instruct-generic-gpu · azureml v2

azureFoundry/azureml/Phi-3-mini-4k-instruct-generic-gpu@2

This model is an optimized version of Phi-3-Mini-4K-Instruct 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 Phi-

Maximum output
2,048
Input modalities
text
Output modalities
text

Phi-3-mini-4k-instruct-openvino-gpu · azureml v2

azureFoundry/azureml/Phi-3-mini-4k-instruct-openvino-gpu@2

This model is an optimized version of Phi-3-Mini-4K-Instruct 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 Phi-3-Mini-4K-Instruct for local

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