Just testing some imatrix stuff. Built using Imatrix_imatrix-with-rp-data.txt done at 4K context (seems best ppl with Nemo fts.)

May randomly disappear at a future date.

GGUF

Model size

12.2B params

Architecture

llama

4-bit

5-bit

6-bit

Inference Providers NEW

This model is not currently available via any of the supported Inference Providers.

The model cannot be deployed to the HF Inference API: The model has no library tag.