HunyuanVideo (13B)
Tencent's frontier 13B dual-stream diffusion transformer for video generation. Produces photorealistic 720p/1080p cinematic video rivaling proprietary models under Apache 2.0.
The brutal truth
The Sora of open source. If you have an RTX 4090 or A6000, the video fidelity destroys everything else on the open market under Apache 2.0.
Files and Versions
Direct inspected tree artifacts from Hugging Face. Verified filenames, exact byte sizes, model weight shards, and configuration definitions.
Files and versions are hosted on Hugging Face. You can view all branches, commits, model weights, and tokenizer artifacts directly.
Inspect tencent/HunyuanVideo /tree/main ↗Inspect /tree/main Repository ↗Decision matrix
✓ RUN / USE THIS IF…
- •You have a 24GB or 48GB GPU
- •You want complete Apache 2.0 rights
- •Your 24GB GPU comfortably fits the model weights (~18GB VRAM) with dedicated headroom for inference.
- •You require 100% offline data privacy with zero third-party API logging, subscriptions, or prompt retention.
✕ WALK AWAY IF…
- •You have under 16GB VRAM (use Wan 2.2 14B instead)
- •Your GPU has less than 18GB VRAM and you cannot tolerate slow CPU/system RAM offload paging.
- •You prefer a plug-and-play web app interface and don't want to manage local model checkpoints, drivers, or runtimes.
- •You need specialized frontier reasoning that exceeds this model's parameter envelope.
True cost of ownership
About
Tencent's frontier 13B dual-stream diffusion transformer for video generation. Produces photorealistic 720p/1080p cinematic video rivaling proprietary models under Apache 2.0.
What it does
Download the weights from Hugging Face, pick a quantisation that matches your GPU, and run it locally with Ollama, llama.cpp, vLLM, or a compatible runtime. Frontier photorealistic physics & cinema generation runs on your own hardware — no per-token bill, no third-party data handling.
Key features
Highest photorealism and physics accuracy of any open video model
Dual-stream video DiT with MLLM text understanding
Apache 2.0 licensing
Use cases
Turn a script into a polished 15–30 second clip.
Visualise shot lists before a full production run.
Fill timeline gaps with convincing atmospheric footage.
Create stylised clips from a lyric sheet or mood board.
Quantization & Hardware Fit
VRAM Hardware Compatibility & Memory Allocation
| Quant | VRAM | Quality / Fit on 24GB | Install / Run Command (COMFYUI) | |
|---|---|---|---|---|
| GGUF Q4● ACTIVE | 18 GB | Standard · ✓ Fits (6GB spare) | comfy model download --url https://huggingface.co/tencent/HunyuanVideo --relative-path models/diffusion_models | |
| FP8 | 24 GB | Standard · ✓ Fits (0GB spare) | comfy model download --url https://huggingface.co/tencent/HunyuanVideo --relative-path models/diffusion_models | |
| BF16 | 44 GB | Standard · ✕ Needs 44GB | comfy model download --url https://huggingface.co/tencent/HunyuanVideo --relative-path models/diffusion_models |
Buyer doubts, cleared
Can I actually run HunyuanVideo (13B) on my 24GB GPU?
What's the fine print on the license?
Does the Text-to-video (Dual-Stream DiT) actually hold up in practice?
User reviews
Solid for frontier photorealistic physics & cinema generation. The learning curve is real but the payoff is there. Start with the smaller build first.
The GGUF Q4 build is the sweet spot. Anything larger needs serious hardware for marginal quality gains.
Used HunyuanVideo (13B) for a client project. Documentation was solid, though the fine-tuning path is less polished than base inference.
Clean interface, consistent results once you land on a prompt you like. Wish there were more export presets for client handoffs.
