command-r
8B parameters
Restricted
Reviewed May 2026

Command R7B (12-2024)

Command R7B (December 2024) is Cohere's smallest model in the Command R family, an 8B-parameter dense transformer with 128K context, trained for retrieval-augmented generation, tool use, and citation generation across 23 languages. It is released under CC-BY-NC-4.0 for research use only; commercial deployment requires Cohere's commercial license.

License: cc-by-nc-4.0·Context: 131,072 tokens
BLK · VERDICT

Our verdict

OP · Fredoline Eruo|VERIFIED MAY 29, 2026
unrated

Excellent model, dangerous license for most operators. Command R7B is one of the best open weights you can run for citation-grounded RAG and structured tool use at the 7-8B tier.

Overview

Command R7B (December 2024) is Cohere's smallest model in the Command R family, an 8B-parameter dense transformer with 128K context, trained for retrieval-augmented generation, tool use, and citation generation across 23 languages. It is released under CC-BY-NC-4.0 for research use only; commercial deployment requires Cohere's commercial license.

Strengths

  • Best-in-class RAG and citation behavior at its size, by design
  • 128K context with strong long-context retrieval performance
  • Native 23-language coverage including Arabic, Hindi, Vietnamese
  • Tool-use templates are first-class, not bolted on

Weaknesses

  • CC-BY-NC-4.0 BLOCKS commercial use — this is a real trap, not a formality
  • Gated download requires Cohere registration and email signup
  • Listed at 7B but actually 8.03B parameters by safetensors count
  • Switching to Cohere's commercial license is a significant procurement event

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_M4.4 GB6 GB

Get the model

HuggingFace

Original weights

huggingface.co/CohereLabs/c4ai-command-r7b-12-2024

Source repository — direct quantization required.

Hardware that runs this

Cards with enough VRAM for at least one quantization of Command R7B (12-2024).

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 Command R7B (12-2024)?

6GB of VRAM is enough to run Command R7B (12-2024) at the Q4_K_M quantization (file size 4.4 GB). Higher-quality quantizations need more.

Can I use Command R7B (12-2024) commercially?

Command R7B (12-2024) is released under the cc-by-nc-4.0, which has restrictions for commercial use. Review the license terms before using it in a product.

What's the context length of Command R7B (12-2024)?

Command R7B (12-2024) supports a context window of 131,072 tokens (about 131K).

Source: huggingface.co/CohereLabs/c4ai-command-r7b-12-2024

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

Related — keep moving

Before you buy

Verify Command R7B (12-2024) runs on your specific hardware before committing money.