SCAIL-2 (character animation) VRAM requirements
June 2026 character animation and replacement built on Wan 2.1 14B: a reference image driven by the motion of another video, without pose skeletons. Native ComfyUI nodes.
TypeVideo
Parameters16B
Fits entirely from13 GB
8-bit or better from22 GB
01The files, and how much VRAM each needs
| File | Size | Needed | Min. VRAM | Quality | Source |
|---|---|---|---|---|---|
| 16-bit | 32.8 GB | 38.1 GB | 39 GB | the original weights | Comfy-Org/SCAIL-2 → |
| Q8_0 | 18.1 GB | 23.4 GB | 24 GB | practically identical to the original | vantagewithai/SCAIL-2-GGUF-ComfyUI → |
| FP8 | 17.7 GB | 23.0 GB | 23 GB | practically identical to the original | Comfy-Org/SCAIL-2 → |
| INT8 | 16.7 GB | 22.0 GB | 22 GB | practically identical to the original | Comfy-Org/SCAIL-2 → |
| Q6_K | 14.2 GB | 19.5 GB | 20 GB | very close to the original | vantagewithai/SCAIL-2-GGUF-ComfyUI → |
| Q5_K_M | 13.0 GB | 18.3 GB | 19 GB | close; small differences in fine detail | vantagewithai/SCAIL-2-GGUF-ComfyUI → |
| Q4_K_M | 11.5 GB | 16.8 GB | 17 GB | good; some loss in fine detail and text | vantagewithai/SCAIL-2-GGUF-ComfyUI → |
| Q3_K_M | 9.1 GB | 14.4 GB | 15 GB | noticeable loss of detail | vantagewithai/SCAIL-2-GGUF-ComfyUI → |
| Q2_K | 7.3 GB | 12.6 GB | 13 GB | heavy loss; a last resort | vantagewithai/SCAIL-2-GGUF-ComfyUI → |
“Needed” = file + 4.5 GB working memory + 0.8 GB system reserve.
02By amount of VRAM
03Best GPU for SCAIL-2
The cheapest cards (by launch price) that run it well, and every card sorted by memory: best GPU for SCAIL-2 → Planning bigger images or longer clips? Open the calculator →
04By graphics card
| GPU | VRAM | Verdict | Best file | Needed |
|---|---|---|---|---|
| Desktop graphics cards | ||||
| RTX 2060 6 GB | 6 GB | Offload only | Q4_K_M | 16.8 GB |
| RTX 3050 6 GB | 6 GB | Offload only | Q4_K_M | 16.8 GB |
| RTX 2070 Super 8 GB | 8 GB | Offload only | Q4_K_M | 16.8 GB |
| RTX 2080 Super 8 GB | 8 GB | Offload only | Q4_K_M | 16.8 GB |
| RTX 3050 8 GB | 8 GB | Offload only | Q4_K_M | 16.8 GB |
| RTX 3060 8 GB | 8 GB | Offload only | Q4_K_M | 16.8 GB |
| RTX 3060 Ti 8 GB | 8 GB | Offload only | Q4_K_M | 16.8 GB |
| RTX 3070 8 GB | 8 GB | Offload only | Q4_K_M | 16.8 GB |
| RTX 3070 Ti 8 GB | 8 GB | Offload only | Q4_K_M | 16.8 GB |
| RTX 4060 8 GB | 8 GB | Offload only | Q4_K_M | 16.8 GB |
| RTX 4060 Ti 8 GB | 8 GB | Offload only | Q4_K_M | 16.8 GB |
| RTX 5050 8 GB | 8 GB | Offload only | Q4_K_M | 16.8 GB |
| RTX 5060 8 GB | 8 GB | Offload only | Q4_K_M | 16.8 GB |
| RTX 5060 Ti 8 GB | 8 GB | Offload only | Q4_K_M | 16.8 GB |
| RX 7600 8 GB | 8 GB | Offload only | Q4_K_M | 16.8 GB |
| RX 9050 8 GB | 8 GB | Offload only | Q4_K_M | 16.8 GB |
| RX 9060 XT 8 GB | 8 GB | Offload only | Q4_K_M | 16.8 GB |
| Arc B570 10 GB | 10 GB | Offload only | Q4_K_M | 16.8 GB |
| RTX 3080 10 GB | 10 GB | Offload only | Q4_K_M | 16.8 GB |
| RTX 2080 Ti 11 GB | 11 GB | Offload only | Q2_K | 12.6 GB |
| Arc B580 12 GB | 12 GB | Offload only | Q2_K | 12.6 GB |
| RTX 2060 12 GB | 12 GB | Offload only | Q2_K | 12.6 GB |
| RTX 3060 12 GB | 12 GB | Offload only | Q2_K | 12.6 GB |
| RTX 3080 12 GB | 12 GB | Offload only | Q2_K | 12.6 GB |
| RTX 3080 Ti 12 GB | 12 GB | Offload only | Q2_K | 12.6 GB |
| RTX 4070 12 GB | 12 GB | Offload only | Q2_K | 12.6 GB |
| RTX 4070 Super 12 GB | 12 GB | Offload only | Q2_K | 12.6 GB |
| RTX 4070 Ti 12 GB | 12 GB | Offload only | Q2_K | 12.6 GB |
| RTX 5070 12 GB | 12 GB | Offload only | Q2_K | 12.6 GB |
| RX 7700 XT 12 GB | 12 GB | Offload only | Q2_K | 12.6 GB |
| RX 9070 GRE 12 GB | 12 GB | Offload only | Q2_K | 12.6 GB |
| Arc A770 16 GB | 16 GB | Tight | Q3_K_M | 14.4 GB |
| RTX 4060 Ti 16 GB | 16 GB | Tight | Q3_K_M | 14.4 GB |
| RTX 4070 Ti Super 16 GB | 16 GB | Tight | Q3_K_M | 14.4 GB |
| RTX 4080 16 GB | 16 GB | Tight | Q3_K_M | 14.4 GB |
| RTX 4080 Super 16 GB | 16 GB | Tight | Q3_K_M | 14.4 GB |
| RTX 5060 Ti 16 GB | 16 GB | Tight | Q3_K_M | 14.4 GB |
| RTX 5070 Ti 16 GB | 16 GB | Tight | Q3_K_M | 14.4 GB |
| RTX 5080 16 GB | 16 GB | Tight | Q3_K_M | 14.4 GB |
| RX 7600 XT 16 GB | 16 GB | Tight | Q3_K_M | 14.4 GB |
| RX 7800 XT 16 GB | 16 GB | Tight | Q3_K_M | 14.4 GB |
| RX 7900 GRE 16 GB | 16 GB | Tight | Q3_K_M | 14.4 GB |
| RX 9060 XT 16 GB | 16 GB | Tight | Q3_K_M | 14.4 GB |
| RX 9070 16 GB | 16 GB | Tight | Q3_K_M | 14.4 GB |
| RX 9070 XT 16 GB | 16 GB | Tight | Q3_K_M | 14.4 GB |
| RX 7900 XT 20 GB | 20 GB | Runs | Q6_K | 19.5 GB |
| Arc Pro B60 24 GB | 24 GB | Runs well | Q8_0 | 23.4 GB |
| RTX 3090 24 GB | 24 GB | Runs well | Q8_0 | 23.4 GB |
| RTX 3090 Ti 24 GB | 24 GB | Runs well | Q8_0 | 23.4 GB |
| RTX 4090 24 GB | 24 GB | Runs well | FP8 | 23.0 GB |
| RX 7900 XTX 24 GB | 24 GB | Runs well | Q8_0 | 23.4 GB |
| Arc Pro B70 32 GB | 32 GB | Runs well | Q8_0 | 23.4 GB |
| RTX 5090 32 GB | 32 GB | Runs well | FP8 | 23.0 GB |
| Laptop GPUs | ||||
| RTX 3050 Laptop 4 GB | 4 GB | Not practical | Q2_K | 12.6 GB |
| RTX 3050 Ti Laptop 4 GB | 4 GB | Not practical | Q2_K | 12.6 GB |
| RTX 2060 Laptop 6 GB | 6 GB | Offload only | Q4_K_M | 16.8 GB |
| RTX 3050 Laptop 6 GB | 6 GB | Offload only | Q4_K_M | 16.8 GB |
| RTX 3060 Laptop 6 GB | 6 GB | Offload only | Q4_K_M | 16.8 GB |
| RTX 4050 Laptop 6 GB | 6 GB | Offload only | Q4_K_M | 16.8 GB |
| RTX 2070 Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 16.8 GB |
| RTX 2070 Super Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 16.8 GB |
| RTX 2080 Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 16.8 GB |
| RTX 2080 Super Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 16.8 GB |
| RTX 3070 Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 16.8 GB |
| RTX 3070 Ti Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 16.8 GB |
| RTX 3080 Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 16.8 GB |
| RTX 4060 Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 16.8 GB |
| RTX 4070 Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 16.8 GB |
| RTX 5050 Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 16.8 GB |
| RTX 5060 Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 16.8 GB |
| RTX 5070 Laptop 8 GB | 8 GB | Offload only | Q4_K_M | 16.8 GB |
| RX 7600M 8 GB | 8 GB | Offload only | Q4_K_M | 16.8 GB |
| RX 7600M XT 8 GB | 8 GB | Offload only | Q4_K_M | 16.8 GB |
| RX 7600S 8 GB | 8 GB | Offload only | Q4_K_M | 16.8 GB |
| RX 7700S 8 GB | 8 GB | Offload only | Q4_K_M | 16.8 GB |
| RTX 4080 Laptop 12 GB | 12 GB | Offload only | Q2_K | 12.6 GB |
| RTX 5070 Laptop 12 GB | 12 GB | Offload only | Q2_K | 12.6 GB |
| RTX 5070 Ti Laptop 12 GB | 12 GB | Offload only | Q2_K | 12.6 GB |
| RX 7800M 12 GB | 12 GB | Offload only | Q2_K | 12.6 GB |
| RTX 3080 Laptop 16 GB | 16 GB | Tight | Q3_K_M | 14.4 GB |
| RTX 3080 Ti Laptop 16 GB | 16 GB | Tight | Q3_K_M | 14.4 GB |
| RTX 4090 Laptop 16 GB | 16 GB | Tight | Q3_K_M | 14.4 GB |
| RTX 5080 Laptop 16 GB | 16 GB | Tight | Q3_K_M | 14.4 GB |
| RX 7900M 16 GB | 16 GB | Tight | Q3_K_M | 14.4 GB |
| RTX 5090 Laptop 24 GB | 24 GB | Runs well | FP8 | 23.0 GB |
| Unified memory | ||||
| Radeon 8060S (Strix Halo) 96 GB | 96 GB | Runs well | 16-bit | 38.1 GB |
| Radeon 8065S (Gorgon Halo) 160 GB | 160 GB | Runs well | 16-bit | 38.1 GB |
| Apple Silicon Macs (by memory) | ||||
| Mac 16 GB | 12.7 GB | Tight | Q2_K | 12.6 GB |
| Mac 18 GB | 14.4 GB | Tight | Q2_K | 12.6 GB |
| Mac 24 GB | 19.6 GB | Runs | Q6_K | 19.5 GB |
| Mac 32 GB | 26.8 GB | Runs well | Q8_0 | 23.4 GB |
| Mac 36 GB | 30.2 GB | Runs well | Q8_0 | 23.4 GB |
| Mac 48 GB | 40.2 GB | Runs well | 16-bit | 38.1 GB |
| Mac 64 GB | 55.7 GB | Runs well | 16-bit | 38.1 GB |
| Mac 96 GB | 85 GB | Runs well | 16-bit | 38.1 GB |
| Mac 128 GB | 115.4 GB | Runs well | 16-bit | 38.1 GB |
| Mac 192 GB | 175.4 GB | Runs well | 16-bit | 38.1 GB |
| Mac 256 GB | 236.9 GB | Runs well | 16-bit | 38.1 GB |
| Mac 512 GB | 498.1 GB | Runs well | 16-bit | 38.1 GB |
05Text encoder, VAE and other files
| File | Folder | Size | When | |
|---|---|---|---|---|
| UMT5-XXL FP8 (scaled) umt5_xxl_fp8_e4m3fn_scaled.safetensors | models/text_encoders | 6.7 GB | text encoder · smaller, recommended | Download → |
| UMT5-XXL FP16 umt5_xxl_fp16.safetensors | models/text_encoders | 11.4 GB | text encoder · alternative | Download → |
| Wan 2.1 VAE BF16 (Kijai) Wan2_1_VAE_bf16.safetensors | models/vae | 0.3 GB | required | Download → |
| CLIP Vision H clip_vision_h.safetensors | models/clip_vision | 1.3 GB | required | Download → |
| SAM 3.1 multiplex FP16 (segmentation) sam3.1_multiplex_fp16.safetensors | models/checkpoints | 1.7 GB | optional · character-replacement workflow (masking) | Download → |
The files the official ComfyUI workflows load next to the model. Sizes read from Hugging Face (2026-10-01).
06Where the files go in ComfyUI
| File | Folder | Loader node |
|---|---|---|
| Diffusion model (.safetensors: 16-bit, FP8, INT8) | ComfyUI/models/diffusion_models | Load Diffusion Model |
| GGUF file (.gguf) | ComfyUI/models/unet | Unet Loader (GGUF) - from the ComfyUI-GGUF node pack |
| Text encoder | ComfyUI/models/text_encoders | Load CLIP / DualCLIPLoader (or the GGUF versions) |
| VAE | ComfyUI/models/vae | Load VAE |
07Measured and reported results
No measured results yet. Send yours.
08Training a LoRA for SCAIL-2
No trainer documentation with a VRAM figure for this model was found yet. What the trainers say for other models →
09Every file tracked for SCAIL-2
| File | Type | Size | Repo |
|---|---|---|---|
| wan2.1_14B_SCAIL_2_fp16.safetensors | F16 | 32.79 GB | Comfy-Org/SCAIL-2 → |
| wan2.1_14B_SCAIL_2_fp8_scaled.safetensors | FP8 | 17.69 GB | Comfy-Org/SCAIL-2 → |
| wan2.1_14B_SCAIL_2_mxfp8.safetensors | MXFP8 | 17.15 GB | Comfy-Org/SCAIL-2 → |
| wan2.1_14B_SCAIL_2_int8_convrot.safetensors | INT8 | 16.65 GB | Comfy-Org/SCAIL-2 → |
| wan2.1_14B_SCAIL_2_nvfp4_mxpf8_mix.safetensors | NVFP4 | 11.02 GB | Comfy-Org/SCAIL-2 → mixed NVFP4/MXFP8 layers (filename 'nvfp4_mxpf8_mix') |
| wan2.1_14B_SCAIL_2-Q8_0.gguf | Q8_0 | 18.15 GB | vantagewithai/SCAIL-2-GGUF-ComfyUI → |
| wan2.1_14B_SCAIL_2-Q6_K.gguf | Q6_K | 14.24 GB | vantagewithai/SCAIL-2-GGUF-ComfyUI → |
| wan2.1_14B_SCAIL_2-Q5_K_M.gguf | Q5_K_M | 12.97 GB | vantagewithai/SCAIL-2-GGUF-ComfyUI → |
| wan2.1_14B_SCAIL_2-Q5_1.gguf | Q5_1 | 12.95 GB | vantagewithai/SCAIL-2-GGUF-ComfyUI → |
| wan2.1_14B_SCAIL_2-Q5_0.gguf | Q5_0 | 12.24 GB | vantagewithai/SCAIL-2-GGUF-ComfyUI → |
| wan2.1_14B_SCAIL_2-Q5_K_S.gguf | Q5_K_S | 12.09 GB | vantagewithai/SCAIL-2-GGUF-ComfyUI → |
| wan2.1_14B_SCAIL_2-Q4_K_M.gguf | Q4_K_M | 11.46 GB | vantagewithai/SCAIL-2-GGUF-ComfyUI → |
| wan2.1_14B_SCAIL_2-Q4_1.gguf | Q4_1 | 11.23 GB | vantagewithai/SCAIL-2-GGUF-ComfyUI → |
| wan2.1_14B_SCAIL_2-Q4_K_S.gguf | Q4_K_S | 10.68 GB | vantagewithai/SCAIL-2-GGUF-ComfyUI → |
| wan2.1_14B_SCAIL_2-Q4_0.gguf | Q4_0 | 10.53 GB | vantagewithai/SCAIL-2-GGUF-ComfyUI → |
| wan2.1_14B_SCAIL_2-Q3_K_M.gguf | Q3_K_M | 9.11 GB | vantagewithai/SCAIL-2-GGUF-ComfyUI → |
| wan2.1_14B_SCAIL_2-Q3_K_S.gguf | Q3_K_S | 8.55 GB | vantagewithai/SCAIL-2-GGUF-ComfyUI → |
| wan2.1_14B_SCAIL_2-Q2_K.gguf | Q2_K | 7.34 GB | vantagewithai/SCAIL-2-GGUF-ComfyUI → |
Pose-free character animation / character replacement from reference image + driving video (zai-org, arXiv 2606.10804). README says 16B params (fp16 file = 32.8 GB). 512p/704p, H and W divisible by 32. Native ComfyUI (WanSCAILToVideo, SCAIL2ColoredMask, SAM3 nodes, no custom nodes); docs workflow also loads Wan2.1 VAE, lightx2v I2V 480p step-distill LoRA, SCAIL-2 DPO LoRA and sam3.1_multiplex_fp16 for masking. GGUF via ComfyUI-GGUF.