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

e5-base-v2

cheaperInference/e5-base-v2

Maximum output
512
Output modalities
embeddings
Capabilities
embeddings

e5-large-v2

cheaperInference/e5-large-v2

Maximum output
512
Output modalities
embeddings
Capabilities
embeddings

EO_OS Object Detection · azureml-spectre-p v1

azureFoundry/azureml-spectre-p/eo-os-object-detection@1

Advanced object detection for Earth Observation and Overhead Sensing imagery.

Input modalities
image
Output modalities
text
Capabilities
visionInput

EvoDiff · azureml v1

azureFoundry/azureml/EvoDiff@1

# Key capabilities ## About this model EvoDiff can unconditionally sample diverse structurally-plausible proteins, generate intrinsically disordered regions, and scaffold structural motifs using only sequence information, challenging a paradigm in structure-based protein design

Maximum output
4,096
Input modalities
text
Output modalities
text

Fara1.5-27B · azureml-cua-ai-frontiers-p v1

azureFoundry/azureml-cua-ai-frontiers-p/Fara1.5-27B@1

Multimodal web agent for browser-based task automation.

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

Fara1.5-4B · azureml-cua-ai-frontiers-p v1

azureFoundry/azureml-cua-ai-frontiers-p/Fara1.5-4B@1

Multimodal web agent for browser-based task automation.

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

Fara1.5-9B · azureml-cua-ai-frontiers-p v1

azureFoundry/azureml-cua-ai-frontiers-p/Fara1.5-9B@1

Multimodal web agent for browser-based task automation.

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

Fara-7B · azureml-msr v2

azureFoundry/azureml-msr/Fara-7B@2

Fara is a multimodal web agent model that observes the browser and acts on behalf of the user by emitting tool‑calls (e.g., click(x,y), type, scroll, select) to complete web tasks end‑to‑end. Fara is trained on data generated by a scalable multi‑agent pipeline that synthesizes di

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

Fara-7B · azureml-msr v3

azureFoundry/azureml-msr/Fara-7B@3

Fara is a multimodal web agent model that observes the browser and acts on behalf of the user by emitting tool‑calls (e.g., click(x,y), type, scroll, select) to complete web tasks end‑to‑end. Fara is trained on data generated by a scalable multi‑agent pipeline that synthesizes di

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

financial-reports-analysis · azureml v1

azureFoundry/azureml/financial-reports-analysis@1

**Description** The adapted AI model for financial reports analysis (preview) is a state\-of\-the\-art small language model (SLM) based on the Phi\-3\-small\-128k architecture, designed specifically for analyzing financial reports. It has been fine\-tuned on a few hundred millio

Input modalities
text
Output modalities
text

financial-reports-analysis · azureml v2

azureFoundry/azureml/financial-reports-analysis@2

**Description** The adapted AI model for financial reports analysis (preview) is a state\-of\-the\-art small language model (SLM) based on the Phi\-3\-small\-128k architecture, designed specifically for analyzing financial reports. It has been fine\-tuned on a few hundred millio

Input modalities
text
Output modalities
text

financial-reports-analysis-v2 · azureml v1

azureFoundry/azureml/financial-reports-analysis-v2@1

Adapted AI model for financial reports analysis based on Phi-4

Context window
16,384
Maximum output
16,384
Input modalities
text
Output modalities
text

FMV Grounding · azureml-spectre-p v1

azureFoundry/azureml-spectre-p/fmv-grounding-detection@1

Closed-set object detection (GroundingDINO) for full-motion video and overhead imagery across land and maritime domains; detects a fixed ontology of six categories (person, ship, vehicle, aircraft, bike, maritime objects).

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

FMV Grounding · azureml-spectre-p v2

azureFoundry/azureml-spectre-p/fmv-grounding-detection@2

Closed-set object detection (GroundingDINO) for full-motion video and overhead imagery across land and maritime domains; detects a fixed ontology of six categories (person, ship, vehicle, aircraft, bike, maritime objects).

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

gemma-4-e2b-it-cuda-gpu · azureml v3

azureFoundry/azureml/gemma-4-e2b-it-cuda-gpu@3

This model is an optimized version of Gemma 4 E2B IT 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 optimized configurat

Maximum output
8,192
Input modalities
text, image, audio
Output modalities
text
Capabilities
audioInput, multimodal, toolCalling, visionInput

gemma-4-e2b-it-generic-cpu · azureml v3

azureFoundry/azureml/gemma-4-e2b-it-generic-cpu@3

This model is an optimized version of Gemma 4 E2B IT 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 the optimized

Maximum output
8,192
Input modalities
text, image, audio
Output modalities
text
Capabilities
audioInput, multimodal, toolCalling, visionInput

gemma-4-e2b-it-generic-gpu · azureml v3

azureFoundry/azureml/gemma-4-e2b-it-generic-gpu@3

This model is an optimized version of Gemma 4 E2B IT 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 are some of the

Maximum output
8,192
Input modalities
text, image, audio
Output modalities
text
Capabilities
audioInput, multimodal, toolCalling, visionInput

GigaTIME · azureml-ai-frontiers v1

azureFoundry/azureml-ai-frontiers/GigaTIME@1

Openweight H&E to mIF translator model

Input modalities
image
Output modalities
image
Capabilities
imageOutput, visionInput

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