Tencent
HunyuanVideo 13B
Tencent's flagship open video model. 720p quality but requires 60+ GB VRAM (or aggressive offloading + tiling).
About This Model
HunyuanVideo is Tencent's answer to closed-source video generation. The output quality rivals commercial tools but the hardware bar is steep — comfortable inference wants an A100 80 GB or H100. Aggressive Q8 quants and tiled VAE bring this down to ~24 GB at the cost of quality.
Check Your Hardware
See which quantizations of HunyuanVideo 13B your hardware can run.
Quantization Options
| Quantization | Bits | File Size | VRAM Needed | RAM Needed | Quality |
|---|---|---|---|---|---|
| FP16 | 16 | 26 GB | 60 GB | 64 GB | 100% |
How to run HunyuanVideo 13B
Pick a runtime — copy & paste. Commands are pre-filled with this model’s repo.
GUI. Browse → download → chat. MLX on Apple Silicon.
LM Studio home →- 1
Open LM Studio
Go to the 🔍 Search tab.
- 2
Search for
tencent/HunyuanVideo - 3
Download
Pick the FP16 quant — best balance of size vs. quality.
- 4
Chat
Hit ▶ Load Model and start chatting. Toggle 'Local Server' to expose an OpenAI-compatible API on :1234.
Community benchmarks
Real seconds-per-image reports from people running HunyuanVideo 13B on actual hardware.
No community runs yet for this model. Be the first to submit your numbers.
Frequently Asked Questions
How much VRAM do I need to run HunyuanVideo 13B?
HunyuanVideo 13B requires 60GB VRAM minimum with FP16 quantization. For full precision, you need 60GB VRAM.
What is the best quantization for HunyuanVideo 13B?
Q4_K_M offers the best balance of quality and VRAM usage. Q8_0 is near-lossless if you have enough VRAM.