stan-hua
/

Llama-3.2-1B-Instruct-AWQ-W4A16

4-bit precision

Model card Files Files and versions Community

Llama-3.2-1B-Instruct-AWQ-W4A16 / model.safetensors

Commit History

AWQ model for meta-llama/Llama-3.2-1B-Instruct: {'w_bit': 4, 'zero_point': True, 'q_group_size': 128, 'version': 'GEMM'}

442b686
verified

stan-hua commited on Jan 1