typhoon2.5 qwen3 30b a3b

Qwen 3

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

Released September 2025262K context≈ 196,608 words30b params

A Thai-language specialist built on Qwen3's mixture-of-experts architecture, activating only 3 billion parameters out of 30 billion per forward pass — keeping inference lean while retaining a broad knowledge base. It handles Thai and multilingual tasks with notable fluency, reflecting Typhoon AI's focus on Southeast Asian language coverage. The sparse activation means it punches above its computational weight, though very complex reasoning chains may still favor denser, larger models.

Capabilities

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

Long Context

Moderate

Multimodal

typhoon2.5 qwen3 30b a3b

Qwen 3

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

Released September 2025262K context≈ 196,608 words30b params

A Thai-language specialist built on Qwen3's mixture-of-experts architecture, activating only 3 billion parameters out of 30 billion per forward pass — keeping inference lean while retaining a broad knowledge base. It handles Thai and multilingual tasks with notable fluency, reflecting Typhoon AI's focus on Southeast Asian language coverage. The sparse activation means it punches above its computational weight, though very complex reasoning chains may still favor denser, larger models.

Capabilities

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

Long Context

Moderate

Multimodal

Glossary

ArchitectureThe underlying structural design of a neural network that defines how data flows through layers and components.Complex ReasoningThe ability to work through multi-step problems, analyze nuanced information, and draw logical conclusions.CoverageThe extent to which training data represents all relevant aspects or regions of a document or domain.Forward PassA single computation cycle where input data flows through the model's layers to produce an output prediction.InferenceThe process of running a trained model to generate predictions or outputs from new inputs.Knowledge BaseA structured or unstructured collection of documents and facts that a system retrieves from to answer queries.MultilingualA model trained to understand and generate text in multiple languages, not just English.ParametersThe learned numerical values in a model — more parameters generally means more capacity but higher compute cost.ReasoningThe model's ability to work through multi-step logical problems and provide justified answers rather than just pattern-matching.Reasoning ChainsA sequence of logical steps a model follows to work through a problem methodically rather than jumping directly to an answer.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