Can the RTX 4090 24 GB run HunyuanVideo (13B, original)?
Yes. FP8 fits on the RTX 4090 24 GB with 6.5 GB to spare.
FP8 (13.2 GB) needs about 17.5 GB in use, so 6.5 GB of the 24 GB stays free: room for a larger image, a LoRA or a ControlNet.
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | hunyuan_video_720_cfgdistill_fp8_e4m3fn.safetensors FP8 · Kijai/HunyuanVideo_comfy | models/diffusion_models | 13.2 GB | Download → |
| Text encoder | llava_llama3_fp8_scaled.safetensors LLaVA-Llama3 FP8 (scaled) · Comfy-Org/HunyuanVideo_repackaged | models/text_encoders | 9.1 GB | Download → |
| Text encoder | clip_l.safetensors CLIP-L · Comfy-Org/HunyuanVideo_repackaged | models/text_encoders | 0.2 GB | Download → |
| VAE | hunyuan_video_vae_bf16.safetensors HunyuanVideo VAE BF16 · Comfy-Org/HunyuanVideo_repackaged | models/vae | 0.5 GB | Download → |
| Total download · keep about the same free on disk | 23.0 GB | |||
Alternatives: LLaVA-Llama3 FP16 (16.1 GB). Only for some workflows: LLaVA-Llama3 vision (0.6 GB, I2V only). Sizes from Hugging Face, 2026-10-01.
02Every HunyuanVideo 13B file on 24 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · Comfy-Org | 25.6 GB | 29.9 GB | 5.9 GB too big | the original weights | Hugging Face → |
| FP8 ← SAFETENSORS · Kijai | 13.2 GB | 17.5 GB | fits · 6.5 GB spare | practically identical to the original | Hugging Face → |
| Q8_0 GGUF · city96 | 14.0 GB | 18.3 GB | fits · 5.7 GB spare | practically identical to the original | Hugging Face → |
| Q6_K GGUF · city96 | 11.0 GB | 15.3 GB | fits · 8.7 GB spare | very close to the original | Hugging Face → |
| Q5_K_M GGUF · city96 | 9.4 GB | 13.7 GB | fits · 10.3 GB spare | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · city96 | 7.9 GB | 12.2 GB | fits · 11.8 GB spare | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · city96 | 6.2 GB | 10.5 GB | fits · 13.5 GB spare | noticeable loss of detail | Hugging Face → |
“Needed” adds 3.5 GB of working memory for HunyuanVideo 13B and a 0.8 GB reserve. Sizes 2026-10-01.
03Measured and reported results
Nobody has sent measured numbers for this pair yet. If you run HunyuanVideo 13B on a RTX 4090 24 GB, send your time per image and peak VRAM and it will appear here, credited.
04About the RTX 4090 24 GB
The RTX 4090 24 GB is an Ada Lovelace GPU with hardware FP8, so ComfyUI can compute Comfy-Org's FP8 files natively: small and fast. (Plain FP8 files use FP8 maths with the --fast fp8_matrix_mult option.)
24 GB GDDR6X · 384-bit · 1008 GB/s · Ada Lovelace. Everything that runs on it →
05Questions
How much VRAM does HunyuanVideo 13B need?
Around 10.5 GB with the smallest file (Q3_K_M) and 17.5 GB with an 8-bit file (FP8). The full 16-bit file needs about 29.9 GB.
Which HunyuanVideo 13B file should I download for the RTX 4090 24 GB?
FP8 (13.2 GB) from Kijai/HunyuanVideo_comfy.
FP8 or Q8_0 for HunyuanVideo 13B on the RTX 4090 24 GB?
FP8 (13.2 GB): the RTX 4090 24 GB computes it natively, while Q8_0 (14.0 GB) is unpacked on the fly.
How much do I need to download for HunyuanVideo 13B on the RTX 4090 24 GB?
23.0 GB: hunyuan_video_720_cfgdistill_fp8_e4m3fn.safetensors, llava_llama3_fp8_scaled.safetensors, clip_l.safetensors, hunyuan_video_vae_bf16.safetensors.