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/azureml/Phi-3-mini-4k-instruct-openvino-npu@2
This model is an optimized version of Phi-3-Mini-4K-Instruct 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 Phi-3-Mini-4K-Instruct for local
- Maximum output
- 2,048
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/phi-3-mini-4k-instruct-qnn-npu@4
This model is an optimized version of phi-3-mini-4k-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-4k-instruct for local i
- Maximum output
- 2,048
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/phi-3-mini-4k-instruct-trtrtx-gpu@2
This model is an optimized version of phi-3-mini-4k-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-4k-instruct fo
- Maximum output
- 2,048
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/Phi-3-mini-4k-instruct-vitis-npu@2
This model is an optimized version of Phi-3-Mini-4K-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 the
- Maximum output
- 2,048
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/Phi-3-mini-128k-instruct@10
Same Phi-3-mini model, but with a larger context size for RAG or few shot prompting.
- Context window
- 131,072
- Maximum output
- 4,096
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/Phi-3-mini-128k-instruct@11
Same Phi-3-mini model, but with a larger context size for RAG or few shot prompting.
- Context window
- 131,072
- Maximum output
- 4,096
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/Phi-3-mini-128k-instruct@12
Same Phi-3-mini model, but with a larger context size for RAG or few shot prompting.
- Context window
- 131,072
- Maximum output
- 4,096
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/Phi-3-mini-128k-instruct@13
Same Phi-3-mini model, but with a larger context size for RAG or few shot prompting.
- Context window
- 131,072
- Maximum output
- 4,096
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/Phi-3-mini-4k-instruct@10
Tiniest member of the Phi-3 family. Optimized for both quality and low latency.
- Context window
- 4,096
- Maximum output
- 4,096
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/Phi-3-mini-4k-instruct@11
Tiniest member of the Phi-3 family. Optimized for both quality and low latency.
- Context window
- 4,096
- Maximum output
- 4,096
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/Phi-3-mini-4k-instruct@13
Tiniest member of the Phi-3 family. Optimized for both quality and low latency.
- Context window
- 4,096
- Maximum output
- 4,096
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/Phi-3-mini-4k-instruct@14
Tiniest member of the Phi-3 family. Optimized for both quality and low latency.
- Context window
- 4,096
- Maximum output
- 4,096
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/Phi-3-mini-4k-instruct@15
Tiniest member of the Phi-3 family. Optimized for both quality and low latency.
- Context window
- 4,096
- Maximum output
- 4,096
- Input modalities
- text
- Output modalities
- text
vertexAI/publishers/microsoft/models/phi3@phi-3-small-128k-instruct
- Input modalities
- text
- Output modalities
- text
Benchmarks
- LiveBench: 24.789%
- Open LLM Leaderboard v2: 31.968%
azureFoundry/azureml/Phi-3-small-128k-instruct@1
## Model Summary The Phi-3-Small-128K-Instruct is a 7B 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 proper
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/Phi-3-small-128k-instruct@2
## Model Summary The Phi-3-Small-128K-Instruct is a 7B 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 proper
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/Phi-3-small-8k-instruct@1
## Model Summary The Phi-3-Small-8K-Instruct is a 7B 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 properti
- Input modalities
- text
- Output modalities
- text
azureFoundry/azureml/Phi-3-small-8k-instruct@2
## Model Summary The Phi-3-Small-8K-Instruct is a 7B 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 properti
- Input modalities
- text
- Output modalities
- text