Guanaco vs. Mistral
LLM Comparison
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
Overview
Mistral is a family of efficient open and hosted models spanning edge deployment through frontier-scale multimodal workloads. Mistral 3 is the current generation.
Mistral AI launched Mistral 7B in September 2023 and followed it with the Mixtral mixture-of-experts models and hosted Small and Large tiers. Mistral 3, released in December 2025 under Apache 2.0, includes dense 3B, 8B, and 14B Ministral models plus Mistral Large 3, a 675B-parameter mixture-of-experts model with 41B active parameters. The family supports instruction tuning, reasoning variants, multilingual use, code, and image understanding.
Initial release: 2023-09-27
Current generation: Mistral 3
Guanaco |
Mistral |
|
|---|---|---|
| Products & Features | ||
| Instruct Models | ||
| Coding Capability | ||
| Customization | ||
| Finetuning | ||
| Open Source | ||
| License | Noncommercial | Apache 2.0 |
| Model Sizes | 7B, 13B, 33B, 65B | 3B, 8B, 14B, 675B (41B active) |