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.
Further reading
Qwen is Alibaba's broad family of open and hosted models for reasoning, coding, multimodal understanding, and agents. Qwen 3.8 Max Preview is the current generation.
Qwen, formerly Tongyi Qianwen, is a family of language and multimodal models developed by Alibaba. It includes general-purpose, coding, vision-language, audio, embedding, and reasoning variants. Qwen 3.8 Max Preview is the current hosted flagship, with support for multimodal and agentic workflows. Earlier Qwen generations, including Qwen 3.6 checkpoints, remain available as Apache 2.0 open weights; availability and licensing should therefore be checked per model.
Further reading