This model is only for testing. It's a reupload of nm-testing/Llama-3_1-8B_2of4_w4a16_gsm8k_256_8196_damp0_1_mse_llm_compressor, renamed to fit into Linux' path length for Unix domain sockets.

Downloads last month
1,929
Safetensors
Model size
1.98B params
Tensor type
I32
BF16
F16
I16
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support

Model tree for danieldk/Llama-3.1-8B-w4a16-int-24

Quantized
(263)
this model