ERNIE-4.5-VL-28B-A3B-Thinking

Name: ERNIE-4.5-VL-28B-A3B-Thinking
Author: Baidu

by BaiduERNIE

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

context N/A28B params

ERNIE-4.5-VL-28B-A3B-Thinking is Baidu's reasoning-focused model that takes a deliberate, step-by-step approach to complex problems, visibly working through its logic before arriving at answers. Despite its 28B parameter count, it uses a sparse 3B active parameter architecture, meaning it punches above its weight in efficiency. It handles text-based reasoning tasks with methodical thoroughness, though its vision capabilities aren't accessible via the current API configuration.

Capabilities

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

Instruction Following

Moderate

Long Context

ERNIE-4.5-VL-28B-A3B-Thinking

by BaiduERNIE

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

context N/A28B params

ERNIE-4.5-VL-28B-A3B-Thinking is Baidu's reasoning-focused model that takes a deliberate, step-by-step approach to complex problems, visibly working through its logic before arriving at answers. Despite its 28B parameter count, it uses a sparse 3B active parameter architecture, meaning it punches above its weight in efficiency. It handles text-based reasoning tasks with methodical thoroughness, though its vision capabilities aren't accessible via the current API configuration.

Capabilities

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

Instruction Following

Moderate

Long Context

Glossary

APIAn interface that allows developers to send requests to and receive responses from an AI model over the internet.ArchitectureThe underlying structural design of a neural network that defines how data flows through layers and components.Parameter CountThe total number of adjustable weights in a model; more parameters generally mean more capacity to learn, but also require more computing power.ReasoningThe model's ability to work through multi-step logical problems and provide justified answers rather than just pattern-matching.Reasoning TasksProblems that require a model to think through multiple steps logically to arrive at an answer, rather than just pattern-matching.Reasoning-FocusedA model specifically trained to work through multi-step logical problems methodically rather than generating quick responses.

Capabilities

Capabilities

Use Case Fit

Glossary