Qwen3-Coder 30B

Good fit for

Developers connecting a local code model to an agent scaffold and repository tools.

Why consider it

The exact entry documents 30B total parameters, approximately 3.3B activated and native 256K context support.

Main limitations

Approximately 3.3B active parameters do not make this a 3.3B-memory model. The family README’s 250GB memory requirement applies to 480B, not this 30B entry. Long contexts need configuration and memory; extrapolated 1M context is not a default. External tooling is needed to edit repositories or execute code.

Cost and access

Local package without a hosted subscription or per-token inference charge. Hardware, electricity and setup remain separate. License: Apache 2.0.

Getting started

Install a compatible Ollama version, review the model license, then run: ollama run qwen3-coder:30b. API access means the local runtime endpoint, not an included hosted API.