Sapling Logo

Guanaco vs. Mistral

LLM Comparison


Guanaco

Guanaco

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

Mistral

Mistral

Overview

Developed by some of the researchers behind Llama, the Mistral large language models are the gold standard for accessible and performant open source models.


Mistral AI offers 7B and a mixture-of-experts 8x7B open source models competitive or better than commercial models of similar size. Available under the Apache 2.0 license, the Mistral models are now also available via most cloud vendors. After releasing their open source models, Mistral AI has also begun offering Small, Large, and Embed models via their business API.


Initial release: 2023-09-27

Looking for an LLM API/SDK that works out of the box? No prompts or ad hoc guardrails.

Sapling API
More Comparisons

Guanaco

Mistral

Products & Features
Instruct Models
Coding Capability
Customization
Finetuning
Open Source
License Noncommercial Apache 2.0
Model Sizes 7B, 13B, 33B, 65B 7B, 8x7B