Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
LoneStriker
/
Meta-Llama-3-70B-Instruct-2.25bpw-h6-exl2
like
6
Text Generation
Transformers
Safetensors
PyTorch
English
llama
facebook
meta
llama-3
conversational
Inference Endpoints
text-generation-inference
exl2
License:
llama3 (other)
Model card
Files
Files and versions
Community
2
Train
Deploy
Use this model
New discussion
New pull request
Resources
PR & discussions documentation
Code of Conduct
Hub documentation
All
Discussions
Pull requests
View closed (0)
Can we get 2 bpw for 24gb cards?
#2 opened about 1 month ago by
MrHillsss
How usable is this low of bpw?
#1 opened about 1 month ago by
Nikerino