Model Intelligence Sheet
smthem/SenseNova-U1-8B-MoT-Merger-gguf overview
ComfyUI 8G Vram node link https://github.com/smthemex/ComfyUI SenseNova U1/tree/main example.jpg Q4 mix Q4mix.png SenseNova U1 8B MoT 8step Q6 TEST enable thin…
Runs locally from ~12.93 GB disk (16 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
13 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| SenseNova-U1-8B-MoT-8step-Q4_K_S.gguf | GGUF | Q4_K_S | 12.93 GB | Download |
| SenseNova-U1-8B-MoT-8step-Q6_K.gguf | GGUF | Q6_K | 14.96 GB | Download |
| SenseNova-U1-8B-MoT-8step-Q8_0.gguf | GGUF | Q8_0 | 18.61 GB | Download |
| SenseNova-U1-8B-MoT-Infographic-Q4_K_S.gguf | GGUF | Q4_K_S | 12.93 GB | Download |
| SenseNova-U1-8B-MoT-Infographic-Q6_K.gguf | GGUF | Q6_K | 14.96 GB | Download |
| SenseNova-U1-8B-MoT-Infographic-Q8_0.gguf | GGUF | Q8_0 | 18.61 GB | Download |
| SenseNova-U1-8B-MoT-Infographic-V3-Q6_K.gguf | GGUF | Q6_K | 14.96 GB | Download |
| SenseNova-U1-8B-MoT-Infographic-V3-Q8_0.gguf | GGUF | Q8_0 | 18.61 GB | Download |
| SenseNova-U1-8B-MoT-Interleaved-Q4_K_S.gguf | GGUF | Q4_K_S | 12.93 GB | Download |
| SenseNova-U1-8B-MoT-Interleaved-Q6_K.gguf | GGUF | Q6_K | 16.71 GB | Download |
| SenseNova-U1-8B-MoT-Q6_K.gguf | GGUF | Q6_K | 14.89 GB | Download |
| SenseNova-U1-8B-MoT-SFT-fm-Q6_K.gguf | GGUF | Q6_K | 14.96 GB | Download |
| SenseNova-U1-8B-MoT-SFT-fm-Q8_0.gguf | GGUF | Q8_0 | 18.61 GB | Download |
Model Details
Model README
---
license: apache-2.0
---
ComfyUI 8G Vram
Q4 mix
SenseNova-U1-8B-MoT-8step Q6 TEST
- enable think
SenseNova-U1-8B-MoT Q6 TEST
Run smthem/SenseNova-U1-8B-MoT-Merger-gguf with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models