Download
1 variant available
fp8 SafeTensor
Chroma-Rapid-AIO-V3-fp8_e5m2.safetensors
8-bit, smaller file • 8.29 GB
Verified: a year ago
License:
Apache 2.0
I've made this model using the https://github.com/lum3on/ComfyUI-ModelQuantizer nodes and the full V48 version, so it could run better in my RX6800.
I know that it is also needed if you want to run TorchCompile in RTX 3000 series, so here you have it.