Command vs. Guanaco

Overview

Command is Cohere's enterprise model family for agents, retrieval-augmented generation, multilingual work, and private deployment. Command A+ is the current open-weight generation.

Cohere develops enterprise language models with an emphasis on retrieval, citations, multilingual applications, tool use, and data sovereignty. Command A+, released in May 2026, is a 218B-parameter mixture-of-experts model with 25B active parameters. It supports text and image input, reasoning, agentic workflows, 48 languages, and private deployment under the Apache 2.0 license.

Initial release: 2021-11-15

Current generation: Command A+

Reference

https://cohere.com/command

Further Reading

• https://cohere.com/blog/command-a-plus

Overview

Guanaco is an LLM based off the QLoRA 4-bit finetuning method developed by Tim Dettmers et. al. in the UW NLP group. Guanaco achieves 99% ChatGPT performance on the Vicuna benchmark.

Guanaco is an LLM that uses a finetuning method called LoRA that was developed by Tim Dettmers et. al. in the UW NLP group. With QLoRA, it becomes possible to finetune up to a 65B parameter model on a 48GB GPU without loss of performance relative to a 16-bit model. The Guanaco model family outperforms all previously released models on the Vicuna benchmark. However, given the models are based off of the LLaMA model family, commercial use is not permitted.

Initial release: 2023-05-23

Reference

https://github.com/artidoro/qlora

Further Reading

• https://arxiv.org/abs/2305.14314
• https://twitter.com/Tim_Dettmers/status/1661379354507476994