solidrust
/

Llama-3-12B-AWQ

Text Generation

4-bit precision

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

Llama-3-12B-AWQ

File size: 82 Bytes

7c0736a

{
  "zero_point": true,
  "q_group_size": 128,
  "w_bit": 4,
  "version": "GEMM"
}