xezpeleta
/

latxa-7b-v1-gguf

Text Generation

Model card Files Files and versions

Latxa 7b GGUF

Provided files

Name	Quant method	Bits	Size	Max RAM required	Use case
latxa-7b-v1.gguf			26 GB
latxa-7b-v1-f16.gguf			13 GB
latxa-7b-v1-q8_0.gguf	Q8_0		6,7 GB

Downloads last month: 38

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

Log In to view the estimation

8-bit

16-bit

View +1 variant

Model tree for xezpeleta/latxa-7b-v1-gguf

Base model

HiTZ/latxa-7b-v1

Quantized

(1)

this model

Space using xezpeleta/latxa-7b-v1-gguf 1