Check my GPU →

Can the RTX 5080 16 GB run HunyuanVideo 1.5?

Yes. FP8 fits on the RTX 5080 16 GB with 3.4 GB to spare.

Video model · 8.3B16 GB GDDR7 · 256-bit · 960 GB/s · BlackwellData 2026-10-01
Runs well
Yes.

Take FP8 (8.3 GB). In use it comes to about 12.6 GB, with 3.4 GB left over on 16 GB.

Best fileFP8
File size8.3 GB
VRAM needed~12.6 GB
System RAM32 GB+
Memory map · RTX 5080 16 GB12.6 GB / 16 GB
08 GB16 GB
Weights FP8 · 8.3 GBWorking memory · 3.5 GBReserve · 0.8 GBFree · 3.4 GB

01What to download

PartFileFolderSize
Modelhunyuanvideo1.5_480p_t2v_cfg_distilled_fp8_scaled.safetensors
FP8 · Comfy-Org/HunyuanVideo_1.5_repackaged
models/diffusion_models8.3 GBDownload →
Text encoderqwen_2.5_vl_7b_fp8_scaled.safetensors
Qwen2.5-VL 7B FP8 (scaled) · Comfy-Org/HunyuanVideo_1.5_repackaged
models/text_encoders9.4 GBDownload →
Text encoderbyt5_small_glyphxl_fp16.safetensors
ByT5 small GlyphXL FP16 · Comfy-Org/HunyuanVideo_1.5_repackaged
models/text_encoders0.4 GBDownload →
VAEhunyuanvideo15_vae_fp16.safetensors
HunyuanVideo 1.5 VAE FP16 · Comfy-Org/HunyuanVideo_1.5_repackaged
models/vae2.5 GBDownload →
Total download · keep about the same free on disk20.7 GB

Alternatives: Qwen2.5-VL 7B BF16 (16.6 GB). Only for some workflows: SigCLIP vision patch14 384 (0.9 GB, I2V only). Sizes from Hugging Face, 2026-10-01.

Free ComfyUI workflow, tested on my RTX 5060 Ti: 480p text to video, FP8 workflow (.json). Drag the file into ComfyUI. All workflows →

02Every HunyuanVideo 1.5 file on 16 GB

FileSizeNeededOn this cardQualityDownload
16-bit
SAFETENSORS · Comfy-Org
16.7 GB21.0 GB5.0 GB too bigthe original weightsHugging Face →
FP8 ←
SAFETENSORS · Comfy-Org
8.3 GB12.6 GBfits · 3.4 GB sparepractically identical to the originalHugging Face →
Q8_0
GGUF · jayn7
9.0 GB13.3 GBfits · 2.7 GB sparepractically identical to the originalHugging Face →
Q6_K
GGUF · jayn7
7.0 GB11.3 GBfits · 4.7 GB sparevery close to the originalHugging Face →
Q5_K_M
GGUF · jayn7
6.1 GB10.4 GBfits · 5.6 GB spareclose; small differences in fine detailHugging Face →
Q4_K_M
GGUF · jayn7
5.1 GB9.4 GBfits · 6.6 GB sparegood; some loss in fine detail and textHugging Face →

“Needed” adds 3.5 GB of working memory for HunyuanVideo 1.5 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 1.5 on a RTX 5080 16 GB, send your time per image and peak VRAM and it will appear here, credited.

04About the RTX 5080 16 GB

The RTX 5080 16 GB is a Blackwell GPU with FP8 and FP4 hardware: ComfyUI computes Comfy-Org's FP8 files natively here, and NVFP4 files (where a model offers them) are faster still.

16 GB GDDR7 · 256-bit · 960 GB/s · Blackwell. Everything that runs on it →

05Questions

How much VRAM does HunyuanVideo 1.5 need?

Around 9.4 GB with the smallest file (Q4_K_M) and 12.6 GB with an 8-bit file (FP8). The full 16-bit file needs about 21.0 GB.

Which HunyuanVideo 1.5 file should I download for the RTX 5080 16 GB?

FP8 (8.3 GB) from Comfy-Org/HunyuanVideo_1.5_repackaged.

FP8 or Q8_0 for HunyuanVideo 1.5 on the RTX 5080 16 GB?

FP8 (8.3 GB): the RTX 5080 16 GB computes it natively, while Q8_0 (9.0 GB) is unpacked on the fly.

How much do I need to download for HunyuanVideo 1.5 on the RTX 5080 16 GB?

20.7 GB: hunyuanvideo1.5_480p_t2v_cfg_distilled_fp8_scaled.safetensors, qwen_2.5_vl_7b_fp8_scaled.safetensors, byt5_small_glyphxl_fp16.safetensors, hunyuanvideo15_vae_fp16.safetensors.