amd-shark
/

sdxl-quant-fp8

Model card Files Files and versions

sdxl-quant-fp8 / linear_conv_fp8_sdpa_fp16_eq_bl

Ctrl+K

Ctrl+K

4 contributors

History: 2 commits

GiusFra's picture

Create config.json

25e566b verified 12 months ago

args.json

1.57 kB

Added models that are fully quantized with FP8. about 1 year ago
config.json

1.68 kB

Create config.json 12 months ago
params.safetensors

5.14 GB
xet

Added models that are fully quantized with FP8. about 1 year ago
quant_params.json

68.2 MB
xet

Added models that are fully quantized with FP8. about 1 year ago
vae.safetensors

167 MB
xet

Added models that are fully quantized with FP8. about 1 year ago