Qwen3 30B A3B Instruct 2507

Planned

qwen/qwen3-30b-a3b-instruct-2507

Qwen3 30B-A3B Instruct is a mixture-of-experts model with 30.5B total parameters and 3.3B active per token. It has a native 262K context window rather than one extended after training, plus tool calling and structured output, making it a strong fit for agent workloads that accumulate long histories.

This model is on the roadmap but is not being served yet, so it will return model_not_found from the API. It appears here because we publish what we intend to run as openly as what we already do — the catalogue should tell you where the platform is going, not just where it is.