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-3.5-mini-instruct-cuda-gpu · azureml v2

azureFoundry/azureml/Phi-3.5-mini-instruct-cuda-gpu@2

This model is an optimized version of Phi-3.5-mini-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-3.5-mini-instruct-generic-cpu · azureml v2

azureFoundry/azureml/Phi-3.5-mini-instruct-generic-cpu@2

This model is an optimized version of Phi-3.5-mini-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-3

Maximum output
2,048
Input modalities
text
Output modalities
text

Phi-3.5-mini-instruct-generic-gpu · azureml v2

azureFoundry/azureml/Phi-3.5-mini-instruct-generic-gpu@2

This model is an optimized version of Phi-3.5-mini-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-3

Maximum output
2,048
Input modalities
text
Output modalities
text

Phi-3.5-mini-instruct-openvino-gpu · azureml v2

azureFoundry/azureml/Phi-3.5-mini-instruct-openvino-gpu@2

This model is an optimized version of Phi-3.5-Mini-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-3.5-Mini-Instruct for local i

Maximum output
2,048
Input modalities
text
Output modalities
text

phi-3.5-mini-instruct-qnn-npu · azureml v3

azureFoundry/azureml/phi-3.5-mini-instruct-qnn-npu@3

This model is an optimized version of phi-3.5-mini-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-3.5-mini-instruct for local inf

Maximum output
2,048
Input modalities
text
Output modalities
text

phi-3.5-mini-instruct-trtrtx-gpu · azureml v2

azureFoundry/azureml/phi-3.5-mini-instruct-trtrtx-gpu@2

This model is an optimized version of Phi-3.5-mini-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-3.5-mini-instruct for

Maximum output
2,048
Input modalities
text
Output modalities
text

Phi-3.5-MoE-instruct

vertexAI/publishers/microsoft/models/phi3@phi-3.5-moe-instruct

Input modalities
text
Output modalities
text

Benchmarks

  • LiveBench: 23.986%
  • Open LLM Leaderboard v2: 36.879%

Phi-3.5-vision instruct (128k) · azureml v2

azureFoundry/azureml/Phi-3.5-vision-instruct@2

Refresh of Phi-3-vision model.

Context window
131,072
Maximum output
4,096
Input modalities
text, image
Output modalities
text
Capabilities
multimodal, visionInput

Phi-3-medium-128k-instruct

vertexAI/publishers/microsoft/models/phi3@phi-3-medium-128k-instruct

Input modalities
text
Output modalities
text

Benchmarks

  • LiveBench: 22.644%
  • Open Ko-LLM Leaderboard: 90.058%
  • Open LLM Leaderboard v1: 72.998%
  • Open LLM Leaderboard v2: 32.026%

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