numen-tech
/

Llama-3.2-3B-Instruct-w4a16g128asym

Text Generation

4-bit precision

Model card Files Files and versions Community

4-bit OmniQuant quantized version of Llama-3.2-3B-Instruct.

Downloads last month: -

Model tree for numen-tech/Llama-3.2-3B-Instruct-w4a16g128asym

Base model

meta-llama/Llama-3.2-3B-Instruct

Quantized

(370)

this model