Latxa 7b Instruct GGUF

Provided files

Name	Quant method	Bits	Size	Max RAM required	Use case
latxa-7b-v1-instruct-q8_0.gguf		8 bits	7 GB	8,2 GB	Fits in a RTX 3060 12Gb

GGUF

Model size

6.74B params

Architecture

llama

Inference Examples

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

Base model

HiTZ/latxa-7b-v1

Adapter

Quantized

(1)

this model