Get started
LLM Index

DeepSeek vs. MPT

A side-by-side comparison of release history, capabilities, licensing and model sizes.

Attribute DeepSeek MPT
Developer DeepSeek MosaicML
Current generation DeepSeek V4 –
Initial release 2023-11-29 2023-05-05
Instruct tuned Yes Yes
Coding Yes No
Finetuning Yes Yes
Open source Yes Yes
License MIT Apache 2.0
Model sizes 284B (13B active), 1.6T (49B active) 7B, 30B
Links

DeepSeek

DeepSeek develops open-weight mixture-of-experts models for reasoning, coding, agents, and efficient long-context inference. DeepSeek V4 is the current generation.

DeepSeek began releasing language models in 2023 with DeepSeek Coder, then gained broad adoption with DeepSeek V3 and the R1 reasoning model in 2024 and 2025. DeepSeek V4, released in April 2026, includes a 284B-parameter Flash model with 13B active parameters and a 1.6T-parameter Pro model with 49B active parameters. Both support one-million-token context windows and are released with open weights under the MIT license.

Further reading

MPT

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.

Further reading

Compare other models

Other DeepSeek comparisons

Other MPT comparisons