Datasheet for local AI49 models98 GPUsData read 2026-09-25
No adsNo tracking
Check my GPU →

Wan 2.2 S2V 14B on 6 GB of VRAM

Video model · 16.3BAny 6 GB GPUData 2026-09-25
No
No, not realistically.

Even the smallest file (Q2_K, 9.5 GB) needs about 14.3 GB, far beyond 6 GB. It may start with heavy offloading, but this is not a realistic everyday setup. Pick a smaller model or a GPU with more memory.

Best fileQ2_K
File size9.5 GB
VRAM needed~14.3 GB
System RAM32 GB+
Memory map · 6 GB GPU14.3 GB needed · 8.3 GB over 6 GB
07 GB14 GB
Weights Q2_K · 9.5 GBWorking memory · 4.0 GBReserve · 0.8 GBSpills to system RAM · 8.3 GB
calculated from real file sizes plus working memory. Not yet measured on this setup. How this works.

Worth trying on NVIDIA GPUs: with an up-to-date ComfyUI, Dynamic VRAM (on by default for NVIDIA since March 2026) streams whatever does not fit from system RAM, and ComfyUI's own start-up message recommends native FP8/INT8 files over GGUF, saying they “will be faster even if they are larger than your memory”. So before settling for a heavily compressed GGUF, try the native FP8 file (16.4 GB). The file recommended above is the best one that fits entirely — the safe choice on older ComfyUI versions, AMD and Intel. Comfy blog: Dynamic VRAM →

01What to download

PartFileFolderSize
ModelWan2.2-S2V-14B-Q2_K.gguf
Q2_K · QuantStack/Wan2.2-S2V-14B-GGUF
models/unet9.5 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_2.2_ComfyUI_Repackaged
models/vae0.3 GBDownload →
Also neededwav2vec2_large_english_fp16.safetensors
wav2vec2 large English FP16 (audio encoder) · Comfy-Org/Wan_2.2_ComfyUI_Repackaged
models/audio_encoders0.6 GBDownload →
Total download · keep about the same free on disk17.1 GB

Alternatives: UMT5-XXL FP16 (11.4 GB). The 16-bit text encoder is a little more faithful; the smaller one is chosen here because it loads faster and needs less RAM. Sizes read from Hugging Face (2026-09-25). “Download” links start the file directly; the file name links are the same files the official ComfyUI workflows use.

System RAM: 32 GB or more. ComfyUI keeps the model file, the text encoder and the VAE in system RAM and moves them to the GPU as needed. With this set of files that is about 17.1 GB, plus roughly 6 GB for Windows, ComfyUI and a browser: 23.1 GB in total. With less RAM it still runs, but Windows starts swapping to disk and loading gets very slow. calculated

02Every file, on 6 GB

FileSizeNeededOn this cardQualityDownload
16-bit
SAFETENSORS · Comfy-Org
32.6 GB37.4 GB31.4 GB too bigthe original weightsHugging Face →
Q8_0
GGUF · QuantStack
19.6 GB24.4 GB18.4 GB too bigpractically identical to the originalHugging Face →
FP8
SAFETENSORS · Comfy-Org
16.4 GB21.2 GB15.2 GB too bigpractically identical to the originalHugging Face →
Q6_K
GGUF · QuantStack
16.2 GB21.0 GB15.0 GB too bigvery close to the originalHugging Face →
Q5_K_M
GGUF · QuantStack
15.0 GB19.8 GB13.8 GB too bigclose; small differences in fine detailHugging Face →
Q4_K_M
GGUF · QuantStack
13.9 GB18.7 GB12.7 GB too biggood; some loss in fine detail and textHugging Face →
Q3_K_M
GGUF · QuantStack
11.4 GB16.2 GB10.2 GB too bignoticeable loss of detailHugging Face →
Q2_K ←
GGUF · QuantStack
9.5 GB14.3 GB8.3 GB too bigheavy loss; a last resortHugging Face →

Sizes from the Hugging Face file listing, read 2026-09-25. “Needed” = file + 4 GB working memory for this model + 0.8 GB kept free for the system.

03The text encoder

UMT5-XXL + wav2vec2: 11.4 GB as 16-bit, 6.7 GB as FP8, 3.7 GB as GGUF Q4_K_M (plus the wav2vec2 audio encoder (0.6 GB)). ComfyUI encodes the prompt first and can push the encoder out of VRAM before sampling, so it does not have to fit together with the model. Use the smallest encoder file; it still fits on its own.