Can the RTX 3070 8 GB run Wan 2.1 I2V 14B 720P?
The smallest sensible file, Q4_K_M (11.3 GB), needs about 18.1 GB — 10.1 GB more than RTX 3070 8 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.
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 (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 →
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 (16.4 GB) on RTX 3070 8 GB, start with blocks_to_swap ≈ 39 (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
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | wan2.1-i2v-14b-720p-Q4_K_M.gguf Q4_K_M · city96/Wan2.1-I2V-14B-720P-gguf | models/unet | 11.3 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_2.1_ComfyUI_repackaged | models/vae | 0.3 GB | Download → |
| Also needed | clip_vision_h.safetensors CLIP Vision H · Comfy-Org/Wan_2.1_ComfyUI_repackaged | models/clip_vision | 1.3 GB | Download → |
| Total download · keep about the same free on disk | 19.6 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 19.6 GB, plus roughly 6 GB for Windows, ComfyUI and a browser: 25.6 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 I2V 720P file on 8 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · Comfy-Org | 32.8 GB | 39.6 GB | 31.6 GB too big | the original weights | Hugging Face → |
| Q8_0 GGUF · city96 | 18.1 GB | 24.9 GB | 16.9 GB too big | practically identical to the original | Hugging Face → |
| FP8 SAFETENSORS · Comfy-Org | 16.4 GB | 23.2 GB | 15.2 GB too big | practically identical to the original | Hugging Face → |
| Q6_K GGUF · city96 | 14.2 GB | 21.0 GB | 13.0 GB too big | very close to the original | Hugging Face → |
| Q5_K_M GGUF · city96 | 12.7 GB | 19.5 GB | 11.5 GB too big | close; small differences in fine detail | Hugging Face → |
| Q4_K_M ← GGUF · city96 | 11.3 GB | 18.1 GB | 10.1 GB too big | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · city96 | 8.6 GB | 15.4 GB | 7.4 GB too big | noticeable loss of detail | Hugging Face → |
Sizes from the Hugging Face file listing, read 2026-09-25. “Needed” = file + 6 GB working memory for this model + 0.8 GB kept free for the system.
03The text encoder
UMT5-XXL + CLIP Vision H: 11.4 GB as 16-bit, 6.7 GB as FP8, 3.7 GB as GGUF Q4_K_M (plus CLIP Vision H (1.3 GB) for the input image). 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 3070 8 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 3070 8 GB: 8 GB GDDR6 · 256-bit · 448 GB/s · Ampere. Everything that runs on the RTX 3070 8 GB →
05What more VRAM would change
With 24 GB you could run Wan 2.1 I2V 720P at 8-bit or better (FP8, 16.4 GB) with no offloading: for example on the RTX 4090 24 GB, RTX 3090 24 GB, RX 7900 XTX 24 GB.
What changes from the RTX 3070 8 GB to the RTX 5060 Ti 16 GB → · What changes from the RTX 3070 8 GB to the RTX 3090 24 GB →
06Measured and reported results
Nobody has sent measured numbers for this pair yet. If you run Wan 2.1 I2V 720P on a RTX 3070 8 GB, send your time per image and peak VRAM and it will appear here, credited.
07Questions
How much VRAM does Wan 2.1 I2V 720P need?
Around 15.4 GB with the smallest file (Q3_K_M) and 23.2 GB with an 8-bit file (FP8), counting working memory and a small system reserve. The full 16-bit file needs about 39.6 GB.
Which Wan 2.1 I2V 720P file should I download for the RTX 3070 8 GB?
Q4_K_M (11.3 GB) from city96/Wan2.1-I2V-14B-720P-gguf. Load it with Unet Loader (GGUF) from the ComfyUI-GGUF node pack.
Is FP8 faster than GGUF on the RTX 3070 8 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 I2V 720P on the RTX 3070 8 GB?
About 19.6 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.