Start Here

North Mini Code home page

Search...

Ask AI

Switch theme

Search

Navigation

Navigation 1. Getting Started 2. Start Here

North Mini Code is Cohere’s coding-focused `30B` total / `3B` active parameter Mixture-of-Experts model for agentic software engineering, terminal tasks, and code generation.

QuickstartRun a first prompt and use the recommended generation settings.Deployment PathsPick between Cohere-hosted, Transformers, vLLM, SGLang, Docker, or AWS paths.Agentic Coding GuideSet up tool calls, chat templates, and multi-step coding-agent loops.Model DetailsReview architecture, context length, training approach, and tool-use behavior.

Core facts: model ID `north-mini-code-1-0`, `256K` context window, `64K` max output, Apache 2.0 license.

• ## Fastest managed path
• ## Fastest local path
• ## Best agent path

Use Cohere’s hosted platform if you want the model without managing weights or inference servers.

• North Mini Code is available on Cohere’s Chat endpoints.
• Cohere’s docs position `Model Vault` as the production path.
• Start here if you care more about speed-to-first-request than local control.

Open the Cohere deployment page

1

Choose your runtime

Pick the path that matches your goal:

• evaluate locally: `/deployment/transformers`
• build an agent server: `/deployment/vllm` or `/deployment/sglang`
• deploy on AWS: `/deployment/sagemaker` or `/deployment/aws-neuron`
• stay managed: `/deployment/cohere-platform`

2

Use the recommended generation settings

Hugging Face’s model card recommends `temperature=1.0` and `top_p=0.95` for generation.

3

Graduate into workflow-specific docs

Once you have a first response working, move into the agent, architecture, FAQ, and troubleshooting pages as needed.

North Mini Code’s `3B` active parameter footprint is why the local paths in this doc set are practical, even though the model has `30B` total parameters.