Downloads · 30 days
5
8% of all-time downloads
Nucleus-Image-FP8-Native
bombman/Nucleus-Image-FP8-Native
Nucleus-Image-FP8-Native is a text-to-image model from bombman. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as creativeml-openrail-m.
This is a native FP8 (float8e4m3fn) quantization of the 17B Nucleus-Image model.
All-time downloads
66
Public
Parameters
16.9B
34.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors34.7 GB · 100%
At a glance
- Task
- Text-to-Image
- Library
- diffusers
- License
- creativeml-openrail-m
- Access
- Public
- Created
- Apr 19, 2026
- Updated
- Apr 19, 2026
- SHA
- 07b2b3b7
Base models
Model card
From the Hugging Face model README
Nucleus-Image-FP8-Native
This is a native FP8 (float8_e4m3fn) quantization of the 17B Nucleus-Image model.
⚠️ VRAM Warning
This model is EXTREMELY HEAVY. Even in FP8, the weights alone take up ~13-14GB of VRAM.
- 16GB VRAM (RTX 4060 Ti / 4070 Ti Super / 4080): Recommended to use with
sequential_cpu_offloadfor stability. Pure GPU inference might OOM at 1024x1024. - 24GB VRAM (RTX 3090 / 4090): Best experience. Can run Pure GPU without offloading.
- 12GB VRAM or less: NOT RECOMMENDED unless using heavy CPU offloading (will be slow).
- Task
- Text-to-Image
- Library
- diffusers
- License
- creativeml-openrail-m
- Created
- Apr 19, 2026
- Updated
- Apr 19, 2026