LLM2023-12-11

Mixtral 8x7B

The first high-performance open MoE model.

Overview

Changed the open source landscape with sparse MoE.

●

Sparse MoE

●

Historic efficiency

●

Open weight

MMLU Score

70.6%

Context32,768 tokens

Params47B (active 13B)

LicenseApache 2.0

ArchMoE

$0 / 1M input tokens

Output: $0 / 1M tokens

✓ Free tier available

European leader in high-performance open-weight AI models.

Prompt Library

Browse Coding Prompts →

Previous Version