This is a 6-bit EXL2 quantization of Aurelian v0.1alpha 70B 32K for testing & feedback. See that page for more details.

This quantization fits in 48GB+24GB (36/24 split) or 3x24GB (16/17/20 split) using Exllamav2 @ 32k context.

Downloads last month: 6

Inference Examples

This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.