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

Can the RTX 3060 12 GB run Wan 2.1 T2V 14B?

Video model · 14B12 GB GDDR6 · 192-bit · 360 GB/s · AmpereData 2026-09-25
Tight
Only just.

Download Q3_K_M (7.6 GB). With the model's working memory it needs about 11.9 GB, leaving 0.1 GB spare on 12 GB. Quality: noticeable loss of detail.

Best fileQ3_K_M
File size7.6 GB
VRAM needed~11.9 GB
System RAM32 GB+
Memory map · RTX 3060 12 GB11.9 GB / 12 GB
06 GB12 GB
Weights Q3_K_M · 7.6 GBWorking memory · 3.5 GBReserve · 0.8 GBFree · 0.1 GB
calculated from real file sizes plus working memory. Not yet measured on this setup. How this works.

Worth trying on this GPU: 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 (14.3 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 →

Using Kijai's WanVideoWrapper instead of the native nodes? Its WanVideo BlockSwap node keeps part of the model in system RAM. To run the FP8 file (14.3 GB) on RTX 3060 12 GB, start with blocks_to_swap ≈ 20 (of 40). Each block is about 0.4 GB; raise the number if you still run out of memory, lower it for speed. estimate WanVideoWrapper →

01What to download

PartFileFolderSize
Modelwan2.1-t2v-14b-Q3_K_M.gguf
Q3_K_M · city96/Wan2.1-T2V-14B-gguf
models/unet7.6 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 disk14.6 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 14.6 GB, plus roughly 6 GB for Windows, ComfyUI and a browser: 20.6 GB in total. With less RAM it still runs, but Windows starts swapping to disk and loading gets very slow. calculated

02Every Wan 2.1 14B file on 12 GB

FileSizeNeededOn this cardQualityDownload
16-bit
SAFETENSORS · Comfy-Org
28.6 GB32.9 GB20.9 GB too bigthe original weightsHugging Face →
Q8_0
GGUF · city96
15.9 GB20.2 GB8.2 GB too bigpractically identical to the originalHugging Face →
FP8
SAFETENSORS · Comfy-Org
14.3 GB18.6 GB6.6 GB too bigpractically identical to the originalHugging Face →
Q6_K
GGUF · city96
12.5 GB16.8 GB4.8 GB too bigvery close to the originalHugging Face →
Q5_K_M
GGUF · city96
11.3 GB15.6 GB3.6 GB too bigclose; small differences in fine detailHugging Face →
Q4_K_M
GGUF · city96
10.1 GB14.4 GB2.4 GB too biggood; some loss in fine detail and textHugging Face →
Q3_K_M ←
GGUF · city96
7.6 GB11.9 GBfits · 0.1 GB sparenoticeable loss of detailHugging Face →

Sizes from the Hugging Face file listing, read 2026-09-25. “Needed” = file + 3.5 GB working memory for this model + 0.8 GB kept free for the system.

03The text encoder

UMT5-XXL: 11.4 GB as 16-bit, 6.7 GB as FP8, 3.7 GB as GGUF Q4_K_M. 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. On 12 GB the FP8 encoder fits on its own, so prompt encoding stays fast.

04About this GPU

The RTX 3060 12 GB (Ampere) has no FP8 compute. FP8 files still load and save memory, but ComfyUI converts them back before the maths, so there is no speed gain — Q8_0 GGUF is the closer-to-original 8-bit choice. ComfyUI can compute INT8 files natively on NVIDIA, which is worth a try where a model offers one.

RTX 3060 12 GB: 12 GB GDDR6 · 192-bit · 360 GB/s · Ampere. Everything that runs on the RTX 3060 12 GB →

06Measured and reported results

Nobody has sent measured numbers for this pair yet. If you run Wan 2.1 14B on a RTX 3060 12 GB, send your time per image and peak VRAM and it will appear here, credited.

07Questions

How much VRAM does Wan 2.1 14B need?

Around 11.9 GB with the smallest file (Q3_K_M) and 18.6 GB with an 8-bit file (FP8), counting working memory and a small system reserve. The full 16-bit file needs about 32.9 GB.

Which Wan 2.1 14B file should I download for the RTX 3060 12 GB?

Q3_K_M (7.6 GB) from city96/Wan2.1-T2V-14B-gguf. Load it with Unet Loader (GGUF) from the ComfyUI-GGUF node pack.

Is FP8 faster than GGUF on the RTX 3060 12 GB?

No. This GPU has no FP8 compute, so ComfyUI converts FP8 weights back before the maths. FP8 only saves memory here; Q8_0 GGUF is the closer-to-original 8-bit pick.

How much do I need to download for Wan 2.1 14B on the RTX 3060 12 GB?

About 14.6 GB for the model file, text encoder and VAE listed on this page, and the same again free on disk. With a 12 GB card, 32 GB of system RAM or more is recommended.