Check my GPU →

HunyuanVideo (13B, original) on 32 GB of VRAM

Yes, but only just: 16-bit leaves 2.1 GB free on 32 GB. The original 13B HunyuanVideo from December 2024. Largely replaced by the lighter HunyuanVideo 1.5, but still widely used with its LoRAs.

Video model · 13BAny 32 GB GPUData 2026-10-01
Runs well
Yes.

Take 16-bit (25.6 GB). In use it comes to about 29.9 GB, with 2.1 GB left over on 32 GB.

Best file16-bit
File size25.6 GB
VRAM needed~29.9 GB
System RAM48 GB+
Memory map · 32 GB GPU29.9 GB / 32 GB
016 GB32 GB
Weights 16-bit · 25.6 GBWorking memory · 3.5 GBReserve · 0.8 GBFree · 2.1 GB

01What to download

PartFileFolderSize
Modelhunyuan_video_t2v_720p_bf16.safetensors
16-bit · Comfy-Org/HunyuanVideo_repackaged
models/diffusion_models25.6 GBDownload →
Text encoderllava_llama3_fp8_scaled.safetensors
LLaVA-Llama3 FP8 (scaled) · Comfy-Org/HunyuanVideo_repackaged
models/text_encoders9.1 GBDownload →
Text encoderclip_l.safetensors
CLIP-L · Comfy-Org/HunyuanVideo_repackaged
models/text_encoders0.2 GBDownload →
VAEhunyuan_video_vae_bf16.safetensors
HunyuanVideo VAE BF16 · Comfy-Org/HunyuanVideo_repackaged
models/vae0.5 GBDownload →
Total download · keep about the same free on disk35.5 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.

System RAM: 48 GB or more. These files take about 35.5 GB of RAM while loaded, 41.5 GB with Windows and ComfyUI. What happens with less. calculated

02Every file, on 32 GB

FileSizeNeededOn this cardQualityDownload
16-bit ←
SAFETENSORS · Comfy-Org
25.6 GB29.9 GBfits · 2.1 GB sparethe original weightsHugging Face →
Q8_0
GGUF · city96
14.0 GB18.3 GBfits · 13.7 GB sparepractically identical to the originalHugging Face →
FP8
SAFETENSORS · Kijai
13.2 GB17.5 GBfits · 14.5 GB sparepractically identical to the originalHugging Face →
Q6_K
GGUF · city96
11.0 GB15.3 GBfits · 16.7 GB sparevery close to the originalHugging Face →
Q5_K_M
GGUF · city96
9.4 GB13.7 GBfits · 18.3 GB spareclose; small differences in fine detailHugging Face →
Q4_K_M
GGUF · city96
7.9 GB12.2 GBfits · 19.8 GB sparegood; some loss in fine detail and textHugging Face →
Q3_K_M
GGUF · city96
6.2 GB10.5 GBfits · 21.5 GB sparenoticeable loss of detailHugging Face →

“Needed” adds 3.5 GB of working memory for HunyuanVideo 13B and a 0.8 GB reserve. Sizes 2026-10-01.