If you downloaded older quants (with no folders) you have to redownload.

There is no support for this in mainline llama.cpp yet. You have to use snowflake-arctic branch: https://github.com/fairydreaming/llama.cpp/tree/snowflake-arctic

Downloads last month: 37

GGUF

Model size

482B params

Architecture

arctic

2-bit

3-bit

4-bit

5-bit

8-bit

Inference Providers NEW

This model is not currently available via any of the supported third-party Inference Providers, and HF Inference API was unable to determine this model's library.