emsi/ mixtral-8x22b

505 2 years ago

The Mixtral-8x22B Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts.

3 models

mixtral-8x22b:latest
9b000033acd8 • 80GB • 64K context window •
Text input • 2 years ago
mixtral-8x22b:q4_0
9b000033acd8 • 80GB • 64K context window •
Text input • 2 years ago
mixtral-8x22b:fp16
062db8dc6277 • 281GB • 64K context window •
Text input • 2 years ago