Downloads · 30 days
4.1K
11% of all-time downloads
realrebelai/SenseNova-U1.5-8B_GGUFs
SenseNova-U1.5-8B_GGUFs is a text-to-image model from realrebelai. Use it when you need an image from a text prompt. It is set up for comfyui. The card lists the license as apache-2.0.
Optimized GGUF quantization formats for SenseNova-U1.5-8B-MoT, tailored for lower-VRAM setups (such as 8GB NVIDIA GPUs) via ComfyUI.
Downloads · 30 days
4.1K
11% of all-time downloads
All-time downloads
36.4K
Public
Repo size
99.9 GB
Likes
20
Trending 1
Click a slice to open those files.
.gguf73.7 GB · 100%
From the Hugging Face model README
Optimized GGUF quantization formats for SenseNova-U1.5-8B-MoT, tailored for lower-VRAM setups (such as 8GB NVIDIA GPUs) via ComfyUI.
The tracking tags above link directly back to the main repository model page to aggregate download statistics.
Files are engineered to balance performance and memory footprints using high-precision F16 tensor swaps for sensitive layers (patch_embedding, dense_embedding, and fm_head) to preserve generation quality:
To run these GGUF files natively without structural AttributeError crashes or shape mismatches, use the dedicated node fork:
👉 GitHub: ComfyUI_SenseNova_U1_REBEL
.gguf file into your ComfyUI models directory (e.g., ComfyUI/models/gguf/).SenseNova_SM_Model loader node and hook it up to the SenseNova_SM_Sampler.