Check my GPU →

Wan 2.1 VACE 14B on 24 GB of VRAM

Yes, but only just: Q8_0 leaves 0.5 GB free on 24 GB. The all-in-one Wan for control and editing: reference-to-video, pose and depth control, inpainting and extending clips.

Video model · 17.3BAny 24 GB GPUData 2026-10-01
Runs well
Yes, just.

Q8_0 (18.7 GB) fits with only 0.5 GB to spare (about 23.5 GB of 24 GB).

Best fileQ8_0
File size18.7 GB
VRAM needed~23.5 GB
System RAM32 GB+
Memory map · 24 GB GPU23.5 GB / 24 GB
012 GB24 GB
Weights Q8_0 · 18.7 GBWorking memory · 4.0 GBReserve · 0.8 GBFree · 0.5 GB

01What to download

PartFileFolderSize
ModelWan2.1_14B_VACE-Q8_0.gguf
Q8_0 · QuantStack/Wan2.1_14B_VACE-GGUF
models/unet18.7 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 →
Total download · keep about the same free on disk25.7 GB

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

02Every file, on 24 GB

FileSizeNeededOn this cardQualityDownload
16-bit
SAFETENSORS · Comfy-Org
34.7 GB39.5 GB15.5 GB too bigthe original weightsHugging Face →
Q8_0 ←
GGUF · QuantStack
18.7 GB23.5 GBfits · 0.5 GB sparepractically identical to the originalHugging Face →
Q6_K
GGUF · QuantStack
14.5 GB19.3 GBfits · 4.7 GB sparevery close to the originalHugging Face →
Q5_K_M
GGUF · QuantStack
13.0 GB17.8 GBfits · 6.2 GB spareclose; small differences in fine detailHugging Face →
Q4_K_M
GGUF · QuantStack
11.6 GB16.4 GBfits · 7.6 GB sparegood; some loss in fine detail and textHugging Face →
Q3_K_S
GGUF · QuantStack
7.8 GB12.6 GBfits · 11.4 GB sparenoticeable loss of detailHugging Face →

“Needed” adds 4 GB of working memory for Wan VACE 14B and a 0.8 GB reserve. Sizes 2026-10-01.