realrebelai/Wan_Dancer_GGUFs overview
<video src="https://cdn uploads.huggingface.co/production/uploads/68761990332d15464ccc8dee/nngAubty5iJDp7iYisq0o.mp4" autoplay loop muted playsinline width="30…
Runs locally from ~9.12 GB disk (12 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Wan-Dancer-14B-Global-Q3_K_M-native.gguf | GGUF | Q3_K_M | 9.12 GB | Download |
| Wan-Dancer-14B-Global-Q4_K_M-native.gguf | GGUF | Q4_K_M | 11.68 GB | Download |
| Wan-Dancer-14B-Global-Q4_K_S-native.gguf | GGUF | Q4_K_S | 10.84 GB | Download |
| Wan-Dancer-14B-Global-Q5_K_M-native.gguf | GGUF | Q5_K_M | 12.99 GB | Download |
| Wan-Dancer-14B-Global-Q6_K-native.gguf | GGUF | Q6_K | 14.38 GB | Download |
| Wan-Dancer-14B-Local-Q3_K_M-native.gguf | GGUF | Q3_K_M | 9.12 GB | Download |
| Wan-Dancer-14B-Local-Q4_K_M-native.gguf | GGUF | Q4_K_M | 11.68 GB | Download |
| Wan-Dancer-14B-Local-Q4_K_S-native.gguf | GGUF | Q4_K_S | 10.84 GB | Download |
| Wan-Dancer-14B-Local-Q5_K_M-native.gguf | GGUF | Q5_K_M | 12.99 GB | Download |
| Wan-Dancer-14B-Local-Q6_K-native.gguf | GGUF | Q6_K | 14.38 GB | Download |
Model Details
| Model ID | realrebelai/Wan_Dancer_GGUFs |
|---|---|
| Author | realrebelai |
| Pipeline | — |
| License | apache-2.0 |
| Base model | Wan-AI/Wan-Dancer-14B |
| Last modified | 2026-07-17T22:22:12.000Z |
Model README
---
base_model: Wan-AI/Wan-Dancer-14B
library_name: gguf
license: apache-2.0
tags:
- wan-dancer
- music-to-dance
- quantization
- gguf
---
<video src="https://cdn-uploads.huggingface.co/production/uploads/68761990332d15464ccc8dee/nngAubty5iJDp7iYisq0o.mp4" autoplay loop muted playsinline width="30%"></video>
REDOWNLOAD QUANTS IF YOU ALREADY DID. THEY PREVIOUS QUANTS WERE CORRUPT!
Wan-Dancer is a hierarchical framework for minute-scale coherent music-to-dance generation.
REQUIRES THE FOLLOWING FILES:
YOU NEED BOTH THE GLOBAL AND LOCAL MODEL (SIMILAR TO WAN 2.2 MODEL FILES WITH HIGH AND LOW)
- TEXT ENCODER - https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/blob/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors
- VAE - https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/blob/main/split_files/vae/wan_2.1_vae.safetensors
- CLIP VISION H - https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/blob/main/split_files/clip_vision/clip_vision_h.safetensors
- DISTILL LORA - https://huggingface.co/lightx2v/Wan2.1-I2V-14B-480P-StepDistill-CfgDistill-Lightx2v/blob/main/loras/Wan21_I2V_14B_lightx2v_cfg_step_distill_lora_rank64.safetensors
workflow includes Rebels Audio Nodes for editing audio pre-generation if needed - https://github.com/RealRebelAI/Rebels_Audio_Nodes
Run realrebelai/Wan_Dancer_GGUFs with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models