My GGUF-IQ-Imatrix quants for the experimental model saishf/Neural-SOVLish-Devil-8B-L3.
The usual Llama-3 presets. Author feedback is apreciated for this experimental model.

Downloads last month: 77

GGUF

Model size

8.03B params

Architecture

llama

3-bit

4-bit

5-bit

6-bit

8-bit

View +1 file

Inference API

Unable to determine this model's library. Check the docs .