MPT vs. Qwen

Overview

MPT-7B and MPT-30B are a set of models that are part of MosaicML's Foundation Series. Trained on 1T tokens, the developers state that MPT-7B matches the performance of LLaMA while also being open source, while MPT-30B outperforms the original GPT-3. In addition to the base model, the developers also offer MPT-Instruct, MPT-Chat, and MPT-7B-StoryWriter-65k+, the last of which is trained on a context length of 65K tokens.

Initial release: 2023-05-05

Reference

https://www.mosaicml.com/blog/mpt-30b

Further Reading

• https://www.mosaicml.com/blog/mpt-7b
• https://huggingface.co/mosaicml

Overview

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.

Initial release: 2023-09-13

Current generation: Qwen 3.8

Reference

https://qwen.ai/

Further Reading

• https://arxiv.org/abs/2309.16609
• https://huggingface.co/Qwen
• https://qwen.ai/blog?id=qwen3.6-35b-a3b