Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
numen-tech
/
Llama-3.2-1B-Instruct-w4a16g128asym
like
0
Text Generation
MLC-LLM
8 languages
conversational
4-bit precision
arxiv:
2308.13137
License:
llama3.2
Model card
Files
Files and versions
Community
Use this model
main
Llama-3.2-1B-Instruct-w4a16g128asym
File size: 55 Bytes
7dd0513
1
2
3
4
5
6
{
"quantization_config"
:
{
"bits"
:
4
}
}