Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
matmelis
/
Llama_3.2_1B_w_int3_qronos
like
0
Safetensors
llama
8-bit precision
quark
Model card
Files
Files and versions
xet
Community
main
Llama_3.2_1B_w_int3_qronos
/
README.md
matmelis
Update README.md
0eba4f4
verified
about 1 month ago
preview
code
|
raw
Copy download link
history
blame
contribute
delete
Safe
83 Bytes
metadata
base_model:
-
meta-llama/Llama-3.2-1B
[INFO] Perplexity: 12.578959465026855