Ovis2.6 30B A3B

Open WeightModel weights are publicly available — can be downloaded and self-hosted

Released February 2026262K context≈ 196,608 words30B params

Ovis2.6 30B A3B is a multimodal specialist that processes both text and images using a mixture-of-experts architecture, activating only 3 billion parameters per forward pass despite having 30 billion total. This makes it unusually efficient for its capability tier — it reasons about visual content without the compute overhead you'd expect from a model its size. The trade-off is that sparse activation can occasionally miss nuance that a fully dense model might catch.

Capabilities

Capability scores are AI-generated based on model documentation, benchmarks, and technical specifications. Learn more

Reasoning & Logic

Strong

Multimodal

Ovis2.6 30B A3B

Open WeightModel weights are publicly available — can be downloaded and self-hosted

Released February 2026262K context≈ 196,608 words30B params

Ovis2.6 30B A3B is a multimodal specialist that processes both text and images using a mixture-of-experts architecture, activating only 3 billion parameters per forward pass despite having 30 billion total. This makes it unusually efficient for its capability tier — it reasons about visual content without the compute overhead you'd expect from a model its size. The trade-off is that sparse activation can occasionally miss nuance that a fully dense model might catch.

Capabilities

Capability scores are AI-generated based on model documentation, benchmarks, and technical specifications. Learn more

Reasoning & Logic

Strong

Multimodal

Glossary

ArchitectureThe underlying structural design of a neural network that defines how data flows through layers and components.Dense ModelA neural network where all parameters are active for every input, in contrast to sparse architectures like mixture-of-experts that selectively activate different parts.Forward PassA single computation cycle where input data flows through the model's layers to produce an output prediction.MultimodalA model that can process and understand multiple types of input, such as both text and images.ParametersThe learned numerical values in a model — more parameters generally means more capacity but higher compute cost.Sparse ActivationA technique where only a subset of a model's parameters are used for each input, reducing computational cost while maintaining performance.

Capabilities

Capabilities

Use Case Fit

Glossary