Can the RTX 3060 Laptop 6 GB run Wan 2.2 T2V A14B?
Not entirely. Even Q4_K_M is 8.0 GB over 6 GB, so ComfyUI keeps part of it in system RAM.
The smallest sensible file, Q4_K_M (9.7 GB), needs about 14.0 GB - 8.0 GB more than RTX 3060 Laptop 6 GB has. ComfyUI can still run it by streaming part of the model from system RAM. How much slower that is depends on your ComfyUI version, the file format and the PCIe link - see the note below.
Also try the FP8 file (14.3 GB) on this GPU. It does not fit entirely, but a current ComfyUI streams the overflow from RAM and native 8-bit files often beat a small GGUF that does fit. 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 Laptop 6 GB, start with blocks_to_swap ≈ 37 (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 →
01With more VRAM
With 20 GB you could run Wan 2.2 T2V at 8-bit or better (Q8_0, 15.4 GB) with no offloading.
What changes from the RTX 3060 Laptop 6 GB to the RTX 5060 Ti 16 GB →
02Every Wan 2.2 T2V file on 6 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · Comfy-Org | 28.6 GB | 32.9 GB | 26.9 GB too big | the original weights | Hugging Face → |
| Q8_0 GGUF · QuantStack | 15.4 GB | 19.7 GB | 13.7 GB too big | practically identical to the original | Hugging Face → |
| FP8 SAFETENSORS · Comfy-Org | 14.3 GB | 18.6 GB | 12.6 GB too big | practically identical to the original | Hugging Face → |
| Q6_K GGUF · QuantStack | 12.0 GB | 16.3 GB | 10.3 GB too big | very close to the original | Hugging Face → |
| Q5_K_M GGUF · QuantStack | 10.8 GB | 15.1 GB | 9.1 GB too big | close; small differences in fine detail | Hugging Face → |
| Q4_K_M ← GGUF · QuantStack | 9.7 GB | 14.0 GB | 8.0 GB too big | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · QuantStack | 7.2 GB | 11.5 GB | 5.5 GB too big | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · QuantStack | 5.3 GB | 9.6 GB | 3.6 GB too big | heavy loss; a last resort | Hugging Face → |
“Needed” adds 3.5 GB of working memory for Wan 2.2 T2V and a 0.8 GB reserve. Sizes 2026-10-01. Wan 2.2 A14B uses two files of this size (high-noise and low-noise); only one sits in VRAM at a time, both must fit in system RAM.
03What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | Wan2.2-T2V-A14B-HighNoise-Q4_K_M.gguf high-noise model (early steps) Q4_K_M · QuantStack/Wan2.2-T2V-A14B-GGUF | models/unet | 9.7 GB | Download → |
| Model | Wan2.2-T2V-A14B-LowNoise-Q4_K_M.gguf low-noise model (late steps) Q4_K_M · QuantStack/Wan2.2-T2V-A14B-GGUF | models/unet | 9.7 GB | Download → |
| Text encoder | umt5_xxl_fp8_e4m3fn_scaled.safetensors UMT5-XXL FP8 (scaled) · Comfy-Org/Wan_2.1_ComfyUI_repackaged | models/text_encoders | 6.7 GB | Download → |
| VAE | wan_2.1_vae.safetensors Wan 2.1 VAE · Comfy-Org/Wan_2.2_ComfyUI_Repackaged | models/vae | 0.3 GB | Download → |
| Total download · keep about the same free on disk | 26.3 GB | |||
Alternatives: UMT5-XXL FP16 (11.4 GB). Sizes from Hugging Face, 2026-10-01.
Free ComfyUI workflow, tested on my RTX 5060 Ti: FP8 workflow (.json) · GGUF Q5_K_M workflow (.json). Drag the file into ComfyUI. All workflows →
System RAM: 48 GB or more. These files (both noise models) take about 26.3 GB of RAM while loaded, 32.3 GB with Windows and ComfyUI. What happens with less. calculated
04The text encoder
Take the smallest UMT5-XXL file (3.7 GB): it is the only one that fits in 6 GB on its own. Sizes: 16-bit 11.4 GB, FP8 6.7 GB, GGUF Q4_K_M 3.7 GB. Why the encoder does not count against VRAM →
05Measured and reported results
Nobody has sent measured numbers for this pair yet. If you run Wan 2.2 T2V on a RTX 3060 Laptop 6 GB, send your time per image and peak VRAM and it will appear here, credited.
06About the RTX 3060 Laptop 6 GB
The RTX 3060 Laptop 6 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. As a laptop GPU it runs at a lower power limit than desktop cards (60–115 W depending on the laptop). The memory verdicts are the same; speed depends heavily on how much power the laptop maker allows.
6 GB GDDR6 · 192-bit · Ampere · 60–115 W. Everything that runs on it →
07Questions
How much VRAM does Wan 2.2 T2V need?
Around 9.6 GB with the smallest file (Q2_K) and 18.6 GB with an 8-bit file (FP8). The full 16-bit file needs about 32.9 GB.
Which Wan 2.2 T2V file should I download for the RTX 3060 Laptop 6 GB?
Q4_K_M (9.7 GB) from QuantStack/Wan2.2-T2V-A14B-GGUF. Load it with Unet Loader (GGUF) from the ComfyUI-GGUF node pack.
FP8 or Q8_0 for Wan 2.2 T2V on the RTX 3060 Laptop 6 GB?
Q8_0 (15.4 GB). The RTX 3060 Laptop 6 GB has no FP8 maths, so FP8 (14.3 GB) only saves memory and is a step further from the original.
How much do I need to download for Wan 2.2 T2V on the RTX 3060 Laptop 6 GB?
26.3 GB: Wan2.2-T2V-A14B-HighNoise-Q4_K_M.gguf, Wan2.2-T2V-A14B-LowNoise-Q4_K_M.gguf, umt5_xxl_fp8_e4m3fn_scaled.safetensors, wan_2.1_vae.safetensors.