DEVELOPER REFERENCE · VERIFIED MODEL EVIDENCE

Compare 22 source-verified model records, repository licenses, published weight formats and dated evidence. No overall model ranking.

Evidence statusSource-first verified
Latest record check2026-11-13
Latest record full verification2026-11-01

DIRECT ANSWER · SOURCE-OBSERVED REGISTRY

What Microsoft model evidence is available?

Open Model Weights currently tracks 22 field-verified Microsoft model records. In this indexed sample, the recorded modalities are 10 Text; 3 Image; 3 Image + text → text; 2 Image To 3D; 1 Audio → text; 1 Not declared; 1 Screenshots and text → GUI/terminal actions; 1 Text → audio. The published repository license labels include 19 mit; 2 apache-2.0; 1 cc-by-nc-sa-4.0. The listed weight formats include Safetensors (17), PyTorch (11), ONNX (1).

Coverage describes the model repositories indexed here, not every model released by the publisher. A checked source, an unknown field and an unchanged source revision are different states. No missing value is treated as a negative answer.

22verified model records
8recorded modalities
3distinct license labels
22model repository links

SOURCE-BACKED PUBLISHER PROFILE

Microsoft: models, research and access

Microsoft Research and other Microsoft teams publish downloadable AI checkpoints for language, vision, document processing, speech and 3D generation. Its verified repository entries range from the Phi small-language-model family to Florence, TRELLIS, VibeVoice and encoder-based models.

These are source-checked model repositories, not a complete Microsoft Foundry catalog. Hosted Microsoft services, specialized decision-scoring APIs and Azure deployment products are separate from downloadable weights; the existence of a Phi checkpoint does not make other Microsoft models open weight.

01

Phi language models versus Florence vision models

The Phi series covers compact language and selected vision-language checkpoints, whereas Florence-2 focuses on visual tasks conditioned by text prompts, including image understanding and captioning. Phi-4 and Phi-3.5-vision-instruct therefore need different prompts, processors and evaluations; a single parameter count is not a capability ranking.

02

TRELLIS image-to-3D research checkpoints

Microsoft's TRELLIS and TRELLIS.2 research projects publish image-to-3D pipelines and downloadable artifacts. These models generate 3D representations or assets, not ordinary text completions. Compare supported input images, artifact size, GPU/runtime dependencies, output export and the specific release repository.

03

VibeVoice and document-specific tasks

VibeVoice-1.5B is described by Microsoft's project as a long-form text-to-speech system, while VibeVoice-ASR is a separate transcription checkpoint. LayoutLMv3 and Table Transformer address layout and document/table understanding. These are distinct model families with different license requirements and inference input pipelines.

04

Repository licenses are model-specific

Most checked Microsoft records show MIT labels, but the registry also includes Apache-2.0 records and a CC BY-NC-SA 4.0 label for LayoutLMv3-base. That label is not a generic Microsoft license; it signals that commercial reuse should not be assumed for that checkpoint. Check the precise revision and license text for any redistribution.

05

Open weights are separate from commercial endpoints

Microsoft also sells model access through cloud services. A hosted Foundry capability is not evidence that a corresponding model checkpoint is redistributable. For an OMW model record, require an independently verified artifact repository and model-specific license before describing it as downloadable open weights.

Publisher background is attributed to official sources. Model counts and license classifications come from OMW repository evidence; no model benchmark or processing location is inferred.

MODEL-BY-MODEL REFERENCE

Which Microsoft model or research family should you inspect?

Browse by published modality and licensing evidence. These are navigation cues, not quality, speed or suitability rankings.

Textmit

phi-4

Language and instruction reasoning

Inspect Phi-4 for its exact architecture, weights and MIT license; confirm runtime and prompts before use.

Commercial use: allowedLicense evidence →
Image + text → textmit

Florence-2-base

Vision task prompting

Use Florence-2-base as the starting point for visual understanding and image-text outputs.

Commercial use: allowedLicense evidence →
Image To 3Dmit

TRELLIS.2-4B

Image-to-3D generation

Review TRELLIS.2-4B for 3D pipeline, artifact exports and system dependencies.

Commercial use: allowedLicense evidence →
Text → audiomit

VibeVoice-1.5B

Text-to-speech generation

Examine VibeVoice-1.5B's documented multi-speaker speech generation workflow.

Commercial use: allowedLicense evidence →
Not declaredcc-by-nc-sa-4.0

layoutlmv3-base

Document layout processing

Inspect LayoutLMv3's non-commercial CC BY-NC-SA 4.0 label rather than assuming universal MIT permission.

Commercial use: not-allowedLicense evidence →

FIELD-BY-FIELD COMPARISON · PRIMARY LINKS

Model evidence at a glance.

Compare the exact entries in our registry. Parameter values are taken from the source-checked record; a license label is not a legal opinion, and recognized weight files are not an inference-speed benchmark. Open each record for the underlying citations and observed history.

Model and parameter countModalityLicense evidenceFormats and filesSource and history
Florence-2-base0.231568B published parametersImage + text → textmitallowed commercial-use classificationLicense file ↗PyTorch, Safetensors2 filesRepository ↗Model evidence →History →
mdeberta-v3-basePending verification published parametersTextmitallowed commercial-use classificationInspect license evidence →PyTorch2 filesRepository ↗Model evidence →History →
TRELLIS-image-largePending verification published parametersImage To 3Dmitallowed commercial-use classificationInspect license evidence →Safetensors8 filesRepository ↗Model evidence →History →
TRELLIS.2-4BPending verification published parametersImage To 3Dmitallowed commercial-use classificationInspect license evidence →Safetensors9 filesRepository ↗Model evidence →History →
deberta-v3-basePending verification published parametersTextmitallowed commercial-use classificationInspect license evidence →PyTorch1 filesRepository ↗Model evidence →History →
BiomedNLP-BiomedBERT-base-uncased-abstract-fulltextPending verification published parametersTextmitallowed commercial-use classificationLicense file ↗PyTorch1 filesRepository ↗Model evidence →History →
table-transformer-structure-recognition0.0288478B published parametersImagemitallowed commercial-use classificationInspect license evidence →PyTorch, Safetensors2 filesRepository ↗Model evidence →History →
deberta-v3-largePending verification published parametersTextmitallowed commercial-use classificationInspect license evidence →PyTorch2 filesRepository ↗Model evidence →History →
VibeVoice-ASR8.67402B published parametersAudio → textmitallowed commercial-use classificationInspect license evidence →Safetensors9 filesRepository ↗Model evidence →History →
layoutlmv3-base0.125327B published parametersNot declaredcc-by-nc-sa-4.0not-allowed commercial-use classificationInspect license evidence →ONNX, PyTorch, Safetensors3 filesRepository ↗Model evidence →History →
deberta-v3-smallPending verification published parametersTextmitallowed commercial-use classificationInspect license evidence →PyTorch1 filesRepository ↗Model evidence →History →
Florence-2-large0.776721B published parametersImage + text → textmitallowed commercial-use classificationLicense file ↗PyTorch, Safetensors2 filesRepository ↗Model evidence →History →
Phi-3.5-mini-instruct3.82108B published parametersTextmitallowed commercial-use classificationLicense file ↗Safetensors3 filesRepository ↗Model evidence →History →
Phi-4-mini-instruct3.83602B published parametersTextmitallowed commercial-use classificationLicense file ↗Safetensors3 filesRepository ↗Model evidence →History →
Phi-3-mini-4k-instruct3.82108B published parametersTextmitallowed commercial-use classificationLicense file ↗Safetensors3 filesRepository ↗Model evidence →History →
Phi-3.5-vision-instruct4.14662B published parametersImage + text → textmitallowed commercial-use classificationLicense file ↗Safetensors3 filesRepository ↗Model evidence →History →
table-transformer-detection0.0288186B published parametersImagemitallowed commercial-use classificationInspect license evidence →PyTorch, Safetensors2 filesRepository ↗Model evidence →History →
phi-414.6595B published parametersTextmitallowed commercial-use classificationLicense file ↗Safetensors7 filesRepository ↗Model evidence →History →
VibeVoice-1.5B2.70402B published parametersText → audiomitallowed commercial-use classificationInspect license evidence →Safetensors4 filesRepository ↗Model evidence →History →
resnet-500.0256102B published parametersImageapache-2.0allowed commercial-use classificationInspect license evidence →PyTorch, Safetensors2 filesRepository ↗Model evidence →History →
phi-22.77968B published parametersTextmitallowed commercial-use classificationLicense file ↗Safetensors3 filesRepository ↗Model evidence →History →
Mage-VL-Cowork 4B4.74179B published parametersScreenshots and text → GUI/terminal actionsapache-2.0allowed commercial-use classificationLicense file ↗Safetensors3 filesRepository ↗Model evidence →History →

LICENSE & COVERAGE · NOT LEGAL ADVICE

How do the recorded licenses differ?

Different models from the same developer can use different license terms. The distribution below describes the labels and field-level classifications observed in the listed repositories; it does not automatically establish permissions for a specific deployment.

License labels

  • mit19 of 22
  • apache-2.02 of 22
  • cc-by-nc-sa-4.01 of 22

Commercial-use classifications

  • allowed21 of 22
  • not-allowed1 of 22

Model modalities

  • Text10 of 22
  • Image3 of 22
  • Image + text → text3 of 22
  • Image To 3D2 of 22
  • Audio → text1 of 22
  • Not declared1 of 22
  • Screenshots and text → GUI/terminal actions1 of 22
  • Text → audio1 of 22

A classification of unknown is not a prohibition. Even a recognized permissive license can carry conditions. Review the license for the exact model and revision. Open the license explorer →

EVIDENCE METHOD · TRANSPARENT LIMITS

How this developer profile is assembled.

We aggregate the current source-checked model records, rather than publish an unverified corporate biography. Repository metadata, model cards, license files and recognized weight artifacts supply the facts where available. The record-check date does not assert that a model or its license changed on that date.

Source-derived runtime signals are not hardware benchmarks. Weight-only memory estimates omit runtime overhead, activations and other deployment requirements. Model-specific uncertainties remain visible in the individual evidence records.

QUESTIONS · DIRECT ANSWERS

Frequently asked questions about Microsoft models.

Which Microsoft models are covered?

Open Model Weights currently lists 22 field-verified records for Microsoft. Their recorded model modalities are: 10 Text; 3 Image; 3 Image + text → text; 2 Image To 3D; 1 Audio → text; 1 Not declared; 1 Screenshots and text → GUI/terminal actions; 1 Text → audio. This is a registry sample, not an exhaustive publisher catalog.

Which licenses are recorded for Microsoft models?

In the 22 indexed records, repository license labels are: 19 mit; 2 apache-2.0; 1 cc-by-nc-sa-4.0. License labels do not replace the model-specific terms or establish rights for every use case.

Where can I verify Microsoft model information?

Each indexed model links to its official source repository and a field-level Open Model Weights profile. The most recent record checks shown here reach 2026-11-13; checking a repository does not imply that its contents changed.

Are Microsoft's Phi and Florence models used for the same task?

No. The published Phi collection covers language and multimodal instruction models, while Florence-2 is designed for prompted image-understanding tasks. The model cards identify their distinct inputs and libraries.

Is every Microsoft model in this registry MIT-licensed?

No. The checked entries include MIT and Apache-2.0 labels, but LayoutLMv3-base carries a CC BY-NC-SA 4.0 label. A model's rights cannot be transferred from another Microsoft release.

Does availability in Microsoft Foundry prove downloadable model weights?

No. An API or managed cloud offering is a service, not a reproducible checkpoint. OMW lists independently checked weight repositories and records the separate licensing evidence for each.

COMPLETE INDEXED SELECTION

All 22 indexed model profiles.