SenseNova U1.5 8B MoT - GGUF Quantizations
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.
Available Quants
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:
- Q8_0 (~21.6 GB) — Near-lossless quality.
- Q6_K (~17.5 GB) — High fidelity.
- Q5_K_M (~15.5 GB) — Balanced tier.
- Q4_K_M (~13.5 GB) — Standard compressed tier.
- Q3_K_M (~10.5 GB) — Recommended tight VRAM profile for 8GB cards.
- Q2_K (~9.4 GB) — Maximum compression.
Required Custom Node Fork
To run these GGUF files natively without structural AttributeError crashes or shape mismatches, use the dedicated node fork:
👉 GitHub: ComfyUI_SenseNova_U1_REBEL
Installation & Usage
- Place your chosen
.gguffile into your ComfyUI models directory (e.g.,ComfyUI/models/gguf/). - Ensure you have installed the ComfyUI_SenseNova_U1_REBEL custom node suite.
- Load the model using the
SenseNova_SM_Modelloader node and hook it up to theSenseNova_SM_Sampler.