Hugging Face's logo

Jimmy1229
/
Llama-3.2-3B-8bit

Text Generation
Transformers
Safetensors
llama
text-generation-inference
8-bit precision
gptq
Model card Files
xet
Community
Llama-3.2-3B-8bit / quantize_config.json

Commit History

AutoGPTQ model for meta-llama/Llama-3.2-3B: 8 bits, gr128, desc_act=False
2650ec3
verified

Jimmy1229 commited on