Mixtral 8x22B

Training compute

2.3×10²⁴ FLOP

Parameters

141B

Published

Apr 17, 2024

Mixtral 8x22B is an AI model developed by Mistral AI (France), first published in April 2024. It works in the language domain, on tasks such as language modeling/generation, code generation, translation and 2 more.

Training it took an estimated 2.3×10²⁴ FLOP of compute (estimation method: operation counting). The model has 141,000,000,000 parameters.

Access: Open weights (unrestricted). Its weights are openly available. Epoch AI rates the confidence of this record as speculative.

Full record

Organization: Mistral AI
Country of organization: France
Domain: Language
Task: Language modeling/generation, Code generation, Translation, Quantitative reasoning, Question answering
Training compute: 2.3×10²⁴ FLOP
Compute estimation method: Operation counting
Parameters: 141,000,000,000
Model accessibility: Open weights (unrestricted)
Open weights: Yes
Epoch confidence: Speculative

Benchmark results

01

Epoch Capabilities Index

ECI Score

121.3