other
30B parameters
Commercial OK
Reviewed July 2026

North Mini Code 1.0

North Mini Code, announced June 9, 2026, is Cohere's first open-weight developer model: a 30B-A3B MoE for agentic coding, small enough in active parameters to run locally. Cohere's official release names Apache-2.0, though at least one report flagged a possibly conflicting non-commercial note on the Hugging Face model card — verify directly against the HF repo before commercial deployment.

License: Apache-2.0·Released Jun 9, 2026·Context: 262,144 tokens

Overview

North Mini Code, announced June 9, 2026, is Cohere's first open-weight developer model: a 30B-A3B MoE for agentic coding, small enough in active parameters to run locally. Cohere's official release names Apache-2.0, though at least one report flagged a possibly conflicting non-commercial note on the Hugging Face model card — verify directly against the HF repo before commercial deployment.

Strengths

  • Cohere's first open-weight model, purpose-built for agentic coding
  • MoE (3B active of 30B total) — light enough to demo on a Mac Studio per the vendor
  • 256K input context

Weaknesses

  • License clarity: Apache-2.0 per the official announcement, but a conflicting non-commercial annotation has been reported on the HF card — confirm before commercial use
  • New vendor entrant to open-weight coding models with limited independent track record

Quantization variants

Each quantization trades model quality for file size and VRAM. Q4_K_M is the most popular starting point.

QuantizationFile sizeVRAM required
Q4_K_M19.0 GB23 GB

Get the model

Ollama

One-line install

ollama run north-mini-code-1.0Read our Ollama review →

Hardware that runs this

Cards with enough VRAM for at least one quantization of North Mini Code 1.0.

Compare alternatives

Models worth comparing

Same parameter band, plus what's one tier above and below — so you can decide what actually fits your hardware.

Frequently asked

What's the minimum VRAM to run North Mini Code 1.0?

23GB of VRAM is enough to run North Mini Code 1.0 at the Q4_K_M quantization (file size 19.0 GB). Higher-quality quantizations need more.

Can I use North Mini Code 1.0 commercially?

Yes — North Mini Code 1.0 ships under the Apache-2.0, which permits commercial use. Always read the license text before deployment.

What's the context length of North Mini Code 1.0?

North Mini Code 1.0 supports a context window of 262,144 tokens (about 262K).

How do I install North Mini Code 1.0 with Ollama?

Run `ollama pull north-mini-code-1.0` to download, then `ollama run north-mini-code-1.0` to start a chat session. The default quantization is Q4_K_M.

Source: Vendor official documentation

Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify model claims.

Related — keep moving

Before you buy

Verify North Mini Code 1.0 runs on your specific hardware before committing money.