TextImage + textCodeTranslation

Cohere Command

Business models: document search with source citations, tool calling, many languages. Command A+ (2026) was the first under Apache 2.0, followed by the North line: code, translation and compact vision.

Developer
Cohere, Canada
First release
Mar 2024
Latest release
Aug 2026
Sizes
2.5B – 218B-A25B
License
Commercial use with conditionsCommand R, R+, R7B, Command A (2024–2025) and North Small Translate: CC-BY-NC, non-commercial only; Command A+ (05-2026), North Mini Code and North Micro Vision: Apache 2.0
Russian
Supported
Ready-made builds
GGUF
Running
Available in OllamaAlso runs without a GPU
Industries
Customer support, Legal, Finance, Documents and accounting
Deploy on your server Hugging Face

What it does

  • Knowledge-base answers with source citations
  • Agents that work with internal systems
  • Translation and correspondence in different languages
  • Analysis of documents with images (A+)

Where it is used

Large companiesCustomer supportLegal and finance departments

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
fits

Versions

  1. North Micro Vision 2.5B / Small Translate
  2. North Mini Code 30B-A3B
  3. Command A+
  4. Command A Vision / Reasoning / Translate
  5. Command A
  6. Command R7B
  7. Command R+
  8. Command R

How to run it

With Ollama — the fastest wayInstall Ollama on your computer or server and find the model in its library by name. Good enough to try the model on your own tasks in one evening.Find it in the Ollama library
On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems. Quantization compresses a model so it takes less video memory and runs on more modest hardware. Answers change slightly, so quality is checked on your own examples.

Frequently asked questions

Can Cohere Command be used in a commercial project?

With conditions. License: Command R, R+, R7B, Command A (2024–2025) and North Small Translate: CC-BY-NC, non-commercial only; Command A+ (05-2026), North Mini Code and North Micro Vision: Apache 2.0. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does Cohere Command need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does Cohere Command support Russian?

Yes, Russian is listed on the model card.

Where can I download Cohere Command and what does it cost?

The Cohere Command weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Comparisons

Similar models

TextAyaCohere Labs · CanadaCommercial use with conditions

Multilingual models from Cohere's research arm, covering 23 to 100+ languages. Tiny Aya (2026, 3.3B) runs on a regular PC, but for non-commercial use only.

DetailsTextJambaAI21 Labs · IsraelCommercial use with conditions

A hybrid of Transformer and Mamba with a window of up to 256K tokens: handles long documents faster than conventional models. Jamba2 focuses on accurate, source-based answers.

DetailsTextIBM GraniteIBM · USACommercial use allowed

IBM enterprise models with transparent training data and ISO 42001 certification. Granite 4 is a memory-efficient Mamba and Transformer hybrid.

Details

Source: huggingface.co/CohereLabs/command-a-plus-05-2026-bf16. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.