Sapling Logo

Koala vs. Mistral

LLM Comparison


Koala

Koala

Overview

Released alongside Vicuna, Koala is one of many descendants of the Meta LLaMA model trained on dialogue data collected from the web. On the developers' benchmarks, Koala outperforms its sibling Alpaca, though its adoption has been significantly less than that of its other sibling, Vicuna. Due to its use of LLaMA, only research use is permitted.



Initial release: 2023-04-03

Further Reading

Mistral

Mistral

Overview

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


Mistral AI offers 7B and mixture-of-experts models (8x7B Mixtral and 8x22B Mixtral) that are 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. The latest Mixtral 8x22B represents state-of-the-art performance in the open-source domain. Mistral AI has also begun offering proprietary Small, Large, and Edge 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

Koala

Mistral

Products & Features
Instruct Models
Coding Capability
Customization
Finetuning
Open Source
License Noncommercial Apache 2.0
Model Sizes 7B, 13B 7B, 8x7B, 8x22B