This repo provides two GGUF quantizations of TheDrummer/Cydonia-22B-v1.3. One is q6_K, one is q4_K_S; both use q8_0 for the output and emedding tensors.

Downloads last month: 23

GGUF

Model size

22.2B params

Architecture

llama

4-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.

Model tree for ddh0/Cydonia-22B-v1.3-GGUF

Base model

TheDrummer/Cydonia-22B-v1.3

Quantized

(15)

this model