North Mini Code
North Mini Code is Cohere’s first North coding model, trained for repository-level software changes and terminal-based agent tasks. Its mixture-of-experts architecture has 30B total parameters and 3B active per token, allowing relatively efficient inference while retaining the memory needs of the full model. Training across multiple agent harnesses targets transferable software engineering behavior rather than a single fixed scaffold. Apache-licensed weights, Chat V2 access, and private Model Vault deployments are available. The documented context limit is 256K with up to 64K output tokens.
2026-06-09
30B total, 3B active
Mixture of Experts
Apache-2.0
Specifications
- Parameters
- 30B total, 3B active
- Architecture
- Mixture of Experts
- License
- Apache-2.0
- Context Window
- 256,000 tokens
- Max Output
- 64,000 tokens
- Type
- text
- Modalities
- text
Benchmark Scores
Advanced Specifications
- Model Family
- North
- API Access
- Available
- Chat Interface
- Available
- Variants
- north-mini-code-1-0
Capabilities & Limitations
- Capabilities
- agentic codingtool usecode generationreasoning
- Known Limitations
- Requires an external harness and tools to execute codeSparse activation does not reduce weight storage to 3BGenerated code requires testing
- Notable Use Cases
- repository maintenancelocal coding agentsterminal automation
- Function Calling Support
- Yes
- Tool Use Support
- Yes
