neuralmagic
/

Llama-3.2-1B-quantized.w8a8

8-bit precision

compressed-tensors

Model card Files Files and versions Community

Llama-3.2-1B-quantized.w8a8

Commit History

Updated compression_config to quantization_config

c634b88
verified

mgoin commited on 28 days ago

Upload folder using huggingface_hub

ef8137d
verified

alexmarques commited on Sep 26

initial commit

dda3a20
verified

alexmarques commited on Sep 26