Sapling Logo

Llama 3.1 vs. MPT

LLM Comparison


Llama 3.1

Llama 3.1

Overview

Llama 3.1 added a 405B flagship model that was the first open-source model competitive with frontier proprietary models, alongside updated 8B and 70B variants with longer context and improved tool use.


Llama 3.1 was a landmark release for open-source AI. The 405B model achieved parity with GPT-4o and Claude 3.5 Sonnet on many benchmarks, marking the first time an open model reached the proprietary frontier. All models support a 128K token context window, multilingual generation in eight languages, and built-in tool-calling capabilities. The permissive license allows commercial use for most organisations, making Llama 3.1 a popular foundation for fine-tuning and self-hosted deployments.


Initial release: 2024-07-23

MPT

MPT

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

Looking for an LLM API/SDK that works out of the box? No prompts or ad hoc guardrails.

Sapling API
More Comparisons

Llama 3.1

MPT

Products & Features
Instruct Models
Coding Capability
Customization
Finetuning
Open Source
License Custom (Commercial OK) Apache 2.0
Model Sizes 8B, 70B, 405B 7B, 30B