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

Can the RTX 4060 Laptop 8 GB run Wan 2.2 TI2V 5B?

Video model · 5B8 GB GDDR6 · 128-bit · Ada Lovelace · 35–115 WData 2026-09-25
Runs
Yes, with a compressed file.

Download Q5_K_M (3.8 GB). With the model's working memory it needs about 7.6 GB, leaving 0.4 GB spare on 8 GB. Quality: close; small differences in fine detail. For better quality, Q6_K (4.2 GB) also runs, with about 0.0 GB spilling into system RAM — a little slower, still practical.

Best fileQ5_K_M
File size3.8 GB
VRAM needed~7.6 GB
System RAM32 GB+
Memory map · RTX 4060 Laptop 8 GB7.6 GB / 8 GB
04 GB8 GB
Weights Q5_K_M · 3.8 GBWorking memory · 3.0 GBReserve · 0.8 GBFree · 0.4 GB
calculated from real file sizes plus working memory. Real-world results people have reported are listed further down. How this works.

Using Kijai's WanVideoWrapper instead of the native nodes? Its WanVideo BlockSwap node keeps part of the model in system RAM. To run the 16-bit file (10.0 GB) on RTX 4060 Laptop 8 GB, start with blocks_to_swap ≈ 19 (of 30). Each block is about 0.3 GB; raise the number if you still run out of memory, lower it for speed. estimate WanVideoWrapper →

01What to download

PartFileFolderSize
ModelWan2.2-TI2V-5B-Q5_K_M.gguf
Q5_K_M · QuantStack/Wan2.2-TI2V-5B-GGUF
models/unet3.8 GBDownload →
Text encoderumt5_xxl_fp8_e4m3fn_scaled.safetensors
UMT5-XXL FP8 (scaled) · Comfy-Org/Wan_2.1_ComfyUI_repackaged
models/text_encoders6.7 GBDownload →
VAEwan2.2_vae.safetensors
Wan 2.2 VAE · Comfy-Org/Wan_2.2_ComfyUI_Repackaged
models/vae1.4 GBDownload →
Total download · keep about the same free on disk12.0 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 12.0 GB, plus roughly 6 GB for Windows, ComfyUI and a browser: 18.0 GB in total. With less RAM it still runs, but Windows starts swapping to disk and loading gets very slow. calculated

02Every Wan 2.2 5B file on 8 GB

FileSizeNeededOn this cardQualityDownload
16-bit
SAFETENSORS · Comfy-Org
10.0 GB13.8 GB5.8 GB too bigthe original weightsHugging Face →
Q8_0
GGUF · QuantStack
5.4 GB9.2 GBspills 1.2 GBpractically identical to the originalHugging Face →
Q6_K
GGUF · QuantStack
4.2 GB8.0 GBspills 0.0 GBvery close to the originalHugging Face →
Q5_K_M ←
GGUF · QuantStack
3.8 GB7.6 GBfits · 0.4 GB spareclose; small differences in fine detailHugging Face →
Q4_K_M
GGUF · QuantStack
3.4 GB7.2 GBfits · 0.8 GB sparegood; some loss in fine detail and textHugging Face →
Q3_K_M
GGUF · QuantStack
2.5 GB6.3 GBfits · 1.7 GB sparenoticeable loss of detailHugging Face →
Q2_K
GGUF · QuantStack
1.9 GB5.7 GBfits · 2.3 GB spareheavy loss; a last resortHugging Face →

Sizes from the Hugging Face file listing, read 2026-09-25. “Needed” = file + 3 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 8 GB the FP8 encoder fits on its own, so prompt encoding stays fast.

04About this GPU

The RTX 4060 Laptop 8 GB is an Ada Lovelace GPU with hardware FP8, so ComfyUI can compute Comfy-Org's FP8 files natively: small and fast. (Plain FP8 files use FP8 maths with the --fast fp8_matrix_mult option.) As a laptop GPU it runs at a lower power limit than desktop cards (35–115 W depending on the laptop). The memory verdicts are the same; speed depends heavily on how much power the laptop maker allows.

RTX 4060 Laptop 8 GB: 8 GB GDDR6 · 128-bit · Ada Lovelace · 35–115 W. Everything that runs on the RTX 4060 Laptop 8 GB →

05What more VRAM would change

With 10 GB you could run Wan 2.2 5B at 8-bit or better (Q8_0, 5.4 GB) with no offloading: for example on the RTX 3080 10 GB.

What changes from the RTX 4060 Laptop 8 GB to the RTX 5060 Ti 16 GB →

06Measured and reported results

LabelSetupResultPeak VRAMDateSource
reportedWan2_2-TI2V-5B_fp8_e4m3fn_scaled_KJ · 480x480 · 30 steps
“30/30 [00:57<00:00, 1.93s/it] ... Prompt executed in 94.93 seconds”
Article says "RTX 4060 (8GB VRAM)", 32 GB RAM, Win 11; same author (lilting) documents this machine as an RTX 4060 Laptop in other posts; I2V; frames not stated; 50 steps = 113.93
94.93 s / clip · 1.93 s/it—2026-03-06lilting.ch →

Reported results are other people's numbers, copied as published, with a link. Settings, drivers and ComfyUI versions differ, so compare them with care. Send yours.

07Questions

How much VRAM does Wan 2.2 5B need?

Around 5.7 GB with the smallest file (Q2_K) and 9.2 GB with an 8-bit file (Q8_0), counting working memory and a small system reserve. The full 16-bit file needs about 13.8 GB.

Which Wan 2.2 5B file should I download for the RTX 4060 Laptop 8 GB?

Q5_K_M (3.8 GB) from QuantStack/Wan2.2-TI2V-5B-GGUF. Load it with Unet Loader (GGUF) from the ComfyUI-GGUF node pack.

Is FP8 faster than GGUF on the RTX 4060 Laptop 8 GB?

It can be. This GPU has FP8 hardware, and ComfyUI computes FP8 natively for files made for it (Comfy-Org's fp8_scaled files), or for any FP8 file with the --fast fp8_matrix_mult option. GGUF files are unpacked on the fly, which costs some speed.

How much do I need to download for Wan 2.2 5B on the RTX 4060 Laptop 8 GB?

About 12.0 GB for the model file, text encoder and VAE listed on this page, and the same again free on disk. With a 8 GB card, 32 GB of system RAM or more is recommended.