DEVELOPER REFERENCE · VERIFIED MODEL EVIDENCE

Compare 9 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 verification2026-11-11

DIRECT ANSWER · SOURCE-OBSERVED REGISTRY

What openbmb model evidence is available?

Open Model Weights currently tracks 9 field-verified openbmb model records. In this indexed sample, the recorded modalities are 3 Text; 2 Any To Any; 1 Image + text → text; 1 Image and text; 1 Text and image; 1 Text → audio. The published repository license labels include 9 apache-2.0. The listed weight formats include Safetensors (9), PyTorch (3), 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.

9verified model records
6recorded modalities
1distinct license labels
9model repository links

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
MiniCPM5-2B2.51676B published parametersTextapache-2.0allowed commercial-use classificationInspect license evidence →Safetensors2 filesRepository ↗Model evidence →History →
VoxCPM22.29B published parametersText → audioapache-2.0allowed commercial-use classificationInspect license evidence →PyTorch, Safetensors2 filesRepository ↗Model evidence →History →
MiniCPM-V 4.7 35B-A3B35B total / about 3B active (publisher multimodal MoE) published parametersText and imageapache-2.0allowed commercial-use classificationInspect license evidence →Safetensors17 filesRepository ↗Model evidence →History →
MiniCPM5-2B-DSpark0.323776B published parametersTextapache-2.0allowed commercial-use classificationInspect license evidence →Safetensors1 filesRepository ↗Model evidence →History →
MiniCPM5-1B1.08063B published parametersTextapache-2.0allowed commercial-use classificationInspect license evidence →Safetensors2 filesRepository ↗Model evidence →History →
MiniCPM-V-4.61.30043B published parametersImage + text → textapache-2.0allowed commercial-use classificationInspect license evidence →Safetensors1 filesRepository ↗Model evidence →History →
MiniCPM-o-4_59.37179B published parametersAny To Anyapache-2.0allowed commercial-use classificationInspect license evidence →ONNX, PyTorch, Safetensors9 filesRepository ↗Model evidence →History →
MiniCPM-OCR 1.01.30043B published parametersImage and textapache-2.0allowed commercial-use classificationInspect license evidence →Safetensors1 filesRepository ↗Model evidence →History →
MiniCPM-o-2_68.675B published parametersAny To Anyapache-2.0allowed commercial-use classificationInspect license evidence →PyTorch, Safetensors6 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

  • apache-2.09 of 9

Commercial-use classifications

  • allowed9 of 9

Model modalities

  • Text3 of 9
  • Any To Any2 of 9
  • Image + text → text1 of 9
  • Image and text1 of 9
  • Text and image1 of 9
  • Text → audio1 of 9

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 openbmb models.

Which openbmb models are covered?

Open Model Weights currently lists 9 field-verified records for openbmb. Their recorded model modalities are: 3 Text; 2 Any To Any; 1 Image + text → text; 1 Image and text; 1 Text and image; 1 Text → audio. This is a registry sample, not an exhaustive publisher catalog.

Which licenses are recorded for openbmb models?

In the 9 indexed records, repository license labels are: 9 apache-2.0. License labels do not replace the model-specific terms or establish rights for every use case.

Where can I verify openbmb 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.

COMPLETE INDEXED SELECTION

All 9 indexed model profiles.