# North Mini Code 1.0

> Cohere's first North-family model: an open Apache-2.0 30B / 3B-active MoE built specifically for agentic coding, 256K context, runs on a single H100.

- Maker: Cohere
- Line: North Mini Code
- Canonical page: https://ai-tldr.dev/models/north-mini-code-1-0/
- Updated: 2026-06-19

## In short

North Mini Code 1.0 is a 30-billion-parameter sparse Mixture-of-Experts model from Cohere Labs, released on June 9, 2026 as the first entry in a new "North" family of open coding models. It has a 256K-token context window. You can use it through Hugging Face (open weights).

## Facts

| Fact | Value | Source |
| --- | --- | --- |
| Context window | 256K (max output 64K tokens) | [1] |
| Licence | Apache-2.0 · open weights | [1] |
| Released | 9 June 2026 | [2] |
| Parameters | 30B total / 3B active (sparse MoE, 128 experts, 8 active per token) | [1] |

## Sources

1. [North-Mini-Code-1.0 model card — Hugging Face](https://huggingface.co/CohereLabs/North-Mini-Code-1.0)
2. [Introducing North Mini Code — Cohere blog](https://cohere.com/blog/north-mini-code)

## Overview

North Mini Code 1.0 is a 30-billion-parameter sparse Mixture-of-Experts model from Cohere Labs, released on June 9, 2026 as the first entry in a new "North" family of open coding models. It activates only 3 billion parameters per token through 128 experts (8 active), runs on a single NVIDIA H100 at FP8, and is distributed on the Hugging Face Hub under Apache 2.0 in BF16, FP8, and W4A16 quantizations.

Cohere positions the model as a coding sub-agent under an orchestrator rather than a general assistant — it is optimized for code generation, agentic software engineering, and terminal tasks, with tool-use and interleaved thinking support. Inputs and outputs are text-only, and the model supports a 256K-token context window with up to 64K output tokens.

Cohere reports 67.6% on SWE-Bench Verified, 40.2% on SWE-Bench Pro, and 36% on Terminal-Bench v2 in its model card, and 33.4 on the Artificial Analysis Coding Index in the launch blog. The company highlights ~2.8x higher output throughput and ~30% lower inter-token latency than Mistral's Devstral Small 2 at comparable accuracy.

## Benchmarks

- SWE-Bench Verified (pass@1): 67.6% ([source](https://huggingface.co/CohereLabs/North-Mini-Code-1.0))
- SWE-Bench Pro: 40.2% ([source](https://huggingface.co/CohereLabs/North-Mini-Code-1.0))
- Terminal-Bench v2: 36% ([source](https://huggingface.co/CohereLabs/North-Mini-Code-1.0))
- Artificial Analysis Coding Index: 33.4% ([source](https://cohere.com/blog/north-mini-code))

## Strengths

- Open weights under a true Apache 2.0 license, with no usage caps or non-compete clauses
- Sparse MoE keeps inference cheap — 3B active parameters of a 30B total network — and fits a single H100 at FP8
- 256K-token context with 64K-token max output, suited to whole-repository agentic coding sessions
- Built specifically for agentic software engineering: tool-use, interleaved thinking, SWE-agent and ReAct harnesses
- Multiple distribution targets out of the box: BF16, FP8, W4A16, plus MLX builds for Apple silicon

## Best for

- Embedded as a coding sub-agent under an orchestrator handling planning and review
- High-volume code execution on fixed hardware where per-token cost matters
- Sovereign and on-premise deployments where source code must stay inside trusted systems
- Local developer setups: a single H100 server or a workstation with MLX on Apple silicon
- Terminal automation and multi-step agentic coding workflows

## How to access

- [Hugging Face (open weights)](https://huggingface.co/CohereLabs/North-Mini-Code-1.0) — model id `CohereLabs/North-Mini-Code-1.0`

## North Mini Code versions

- North Mini Code 1.0 (9 June 2026): First model in the North family — agentic coding sub-agent under Apache 2.0. — this page

## FAQ

### What is North Mini Code 1.0?

It is the first model in Cohere Labs' new "North" family — a 30B-parameter sparse Mixture-of-Experts model (3B active per token) released on June 9, 2026 under Apache 2.0. It is purpose-built as a coding sub-agent: it handles code generation, agentic software engineering, and terminal tasks with tool use and interleaved thinking.

### What hardware does North Mini Code 1.0 need?

The FP8 build fits on a single NVIDIA H100. Cohere also publishes a W4A16 quantization for smaller deployments and an MLX-compatible build that runs locally on Apple silicon at roughly 20 GB of RAM.

### What is the context window and what modalities does it support?

256K-token input context and up to 64K output tokens per generation. Inputs and outputs are text only — North Mini Code is not multimodal.

### How does North Mini Code compare to Devstral Small 2?

On Cohere's launch comparison, North Mini Code reaches roughly 2.8x the output throughput and 30% lower inter-token latency than Devstral Small 2 at competitive coding accuracy, scoring 33.4 on the Artificial Analysis Coding Index.

## Links

- [Introducing North Mini Code — Cohere blog](https://cohere.com/blog/north-mini-code)
- [North-Mini-Code-1.0 model card — Hugging Face](https://huggingface.co/CohereLabs/North-Mini-Code-1.0)
- [North-Mini-Code-1.0 FP8 — Hugging Face](https://huggingface.co/CohereLabs/North-Mini-Code-1.0-fp8)
- [North-Mini-Code-1.0 W4A16 — Hugging Face](https://huggingface.co/CohereLabs/North-Mini-Code-1.0-w4a16)
- [North Mini Code 1.0 docs — Cohere](https://docs.cohere.com/docs/north-mini-code-1.0)
- [Cohere North Mini Code release coverage — Digital Applied](https://www.digitalapplied.com/blog/cohere-north-mini-code-open-source-30b-coding-model-release)

Source: AI/TLDR LLM registry, https://ai-tldr.dev/models/north-mini-code-1-0/