Can the RTX 3090 24 GB run Wan 2.2 I2V A14B?
Yes. Q8_0 fits on the RTX 3090 24 GB with 4.3 GB to spare.
Take Q8_0 (15.4 GB). In use it comes to about 19.7 GB, with 4.3 GB left over on 24 GB.
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | Wan2.2-I2V-A14B-HighNoise-Q8_0.gguf high-noise model (early steps) Q8_0 · QuantStack/Wan2.2-I2V-A14B-GGUF | models/unet | 15.4 GB | Download → |
| Model | Wan2.2-I2V-A14B-LowNoise-Q8_0.gguf low-noise model (late steps) Q8_0 · QuantStack/Wan2.2-I2V-A14B-GGUF | models/unet | 15.4 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 | 37.8 GB | |||
Alternatives: UMT5-XXL FP16 (11.4 GB). Sizes from Hugging Face, 2026-10-01.
System RAM: 48 GB or more. These files (both noise models) take about 37.8 GB of RAM while loaded, 43.8 GB with Windows and ComfyUI. What happens with less. calculated
02Every Wan 2.2 I2V file on 24 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · Comfy-Org | 28.6 GB | 32.9 GB | 8.9 GB too big | the original weights | Hugging Face → |
| Q8_0 ← GGUF · QuantStack | 15.4 GB | 19.7 GB | fits · 4.3 GB spare | practically identical to the original | Hugging Face → |
| FP8 SAFETENSORS · Comfy-Org | 14.3 GB | 18.6 GB | fits · 5.4 GB spare | practically identical to the original | Hugging Face → |
| Q6_K GGUF · QuantStack | 12.0 GB | 16.3 GB | fits · 7.7 GB spare | very close to the original | Hugging Face → |
| Q5_K_M GGUF · QuantStack | 10.8 GB | 15.1 GB | fits · 8.9 GB spare | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · QuantStack | 9.7 GB | 14.0 GB | fits · 10.0 GB spare | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · QuantStack | 7.2 GB | 11.5 GB | fits · 12.5 GB spare | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · QuantStack | 5.3 GB | 9.6 GB | fits · 14.4 GB spare | heavy loss; a last resort | Hugging Face → |
“Needed” adds 3.5 GB of working memory for Wan 2.2 I2V 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.
03Measured and reported results
Nobody has sent measured numbers for this pair yet. If you run Wan 2.2 I2V on a RTX 3090 24 GB, send your time per image and peak VRAM and it will appear here, credited.
04About the RTX 3090 24 GB
The RTX 3090 24 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.
24 GB GDDR6X · 384-bit · 936 GB/s · Ampere. Everything that runs on it →
05Questions
How much VRAM does Wan 2.2 I2V 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 I2V file should I download for the RTX 3090 24 GB?
Q8_0 (15.4 GB) from QuantStack/Wan2.2-I2V-A14B-GGUF. Load it with Unet Loader (GGUF) from the ComfyUI-GGUF node pack.
FP8 or Q8_0 for Wan 2.2 I2V on the RTX 3090 24 GB?
Q8_0 (15.4 GB). The RTX 3090 24 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 I2V on the RTX 3090 24 GB?
37.8 GB: Wan2.2-I2V-A14B-HighNoise-Q8_0.gguf, Wan2.2-I2V-A14B-LowNoise-Q8_0.gguf, umt5_xxl_fp8_e4m3fn_scaled.safetensors, wan_2.1_vae.safetensors.