amd-shark
/

sdxl-quant-fp8

Model card Files Files and versions Community

sdxl-quant-fp8 / linear_conv_fp8_sdpa_fp8_no_eq_bl

4 contributors

History: 1 commit

nickfraser's picture

Added models that are fully quantized with FP8.

cfd94d7 3 months ago

args.json

1.57 kB

Added models that are fully quantized with FP8. 3 months ago
params.safetensors

5.14 GB
LFS

Added models that are fully quantized with FP8. 3 months ago
quant_params.json

68.8 MB
LFS

Added models that are fully quantized with FP8. 3 months ago
vae.safetensors

167 MB
LFS

Added models that are fully quantized with FP8. 3 months ago