Check my GPU →

Wan 2.1 I2V 14B 480P on 24 GB of VRAM

Yes, but only just: Q8_0 leaves 1.6 GB free on 24 GB. The image-to-video Wan 2.1, trained for 832×480. It has extra image-conditioning layers, so its files are bigger than the text-to-video 14B.

Video model · 16.4BAny 24 GB GPUData 2026-10-01
Runs well
Yes, just.

Q8_0 (18.1 GB) fits with only 1.6 GB to spare (about 22.4 GB of 24 GB).

Best fileQ8_0
File size18.1 GB
VRAM needed~22.4 GB
System RAM48 GB+
Memory map · 24 GB GPU22.4 GB / 24 GB
012 GB24 GB
Weights Q8_0 · 18.1 GBWorking memory · 3.5 GBReserve · 0.8 GBFree · 1.6 GB

Got an RTX 40 or 50? Swap Q8_0 for FP8 (16.4 GB): same quality class, computed natively there.

01What to download

PartFileFolderSize
Modelwan2.1-i2v-14b-480p-Q8_0.gguf
Q8_0 · city96/Wan2.1-I2V-14B-480P-gguf
models/unet18.1 GBDownload →
Text encoderumt5_xxl_fp8_e4m3fn_scaled.safetensors
UMT5-XXL FP8 (scaled) · Comfy-Org/Wan_2.1_ComfyUI_repackaged
models/text_encoders6.7 GBDownload →
VAEwan_2.1_vae.safetensors
Wan 2.1 VAE · Comfy-Org/Wan_2.1_ComfyUI_repackaged
models/vae0.3 GBDownload →
Also neededclip_vision_h.safetensors
CLIP Vision H · Comfy-Org/Wan_2.1_ComfyUI_repackaged
models/clip_vision1.3 GBDownload →
Total download · keep about the same free on disk26.4 GB

Alternatives: UMT5-XXL FP16 (11.4 GB). Sizes from Hugging Face, 2026-10-01.

System RAM: 48 GB or more. These files take about 26.4 GB of RAM while loaded, 32.4 GB with Windows and ComfyUI. What happens with less. calculated

02Every file, on 24 GB

FileSizeNeededOn this cardQualityDownload
16-bit
SAFETENSORS · Comfy-Org
32.8 GB37.1 GB13.1 GB too bigthe original weightsHugging Face →
Q8_0 ←
GGUF · city96
18.1 GB22.4 GBfits · 1.6 GB sparepractically identical to the originalHugging Face →
FP8
SAFETENSORS · Comfy-Org
16.4 GB20.7 GBfits · 3.3 GB sparepractically identical to the originalHugging Face →
Q6_K
GGUF · city96
14.2 GB18.5 GBfits · 5.5 GB sparevery close to the originalHugging Face →
Q5_K_M
GGUF · city96
12.7 GB17.0 GBfits · 7.0 GB spareclose; small differences in fine detailHugging Face →
Q4_K_M
GGUF · city96
11.3 GB15.6 GBfits · 8.4 GB sparegood; some loss in fine detail and textHugging Face →
Q3_K_M
GGUF · city96
8.6 GB12.9 GBfits · 11.1 GB sparenoticeable loss of detailHugging Face →

“Needed” adds 3.5 GB of working memory for Wan 2.1 I2V 480P and a 0.8 GB reserve. Sizes 2026-10-01.