Updated: Apr 18, 2026
base modelDownload
1 variant available
fp8 SafeTensor
ernie-image-turbo-mxfp8.safetensors
8-bit, smaller file β’ 9.9 GB
Verified: 4 months ago
Stats
9570 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
Reviews
(49)
Published
Apr 16, 2026
Base Model
Ernie
Hash
AutoV2
979B4025FE
License:
Ernie in different quants:
Mixed FP8 - Mostly fp8_e4m3 some are not quantized, fast.
Mixed NVFP4 - NVFP4 except final layers to give a higher quality finish, faster than FP8
NVFP4 - Mostly NVFP4 - Fastest
Note: You will only see speedups from NVFP4 on Blackwell series NVIDIA cards.
https://ernie.baidu.com/blog/posts/ernie-image/
text_encoders
vae
Model Storage Location
π ComfyUI/
βββ π models/
β βββ π diffusion_models/
β β βββ ernie-image-turbo-nvfp4.safetensors
β βββ π text_encoders/
β β βββ ministral-3-3b.safetensors
β β βββ ernie-image-prompt-enhancer.safetensors
β βββ π vae/
β βββ flux2-vae.safetensors

