| File | illustrious_fp8_e4m3fn.safetensors |
| Model | Illustrious XL / Pony (SDXL anime) (image model, 3.5B) |
| Precision | FP8 |
| Size | 3.5 GB |
| VRAM to fit | about 5.5 GB |
| Folder | ComfyUI/models/diffusion_models/ |
| Loader node | Load Diffusion Model (UNETLoader) |
| Source | calcuis/illustrious on Hugging Face |
Download illustrious_fp8_e4m3fn.safetensors (3.5 GB)
Where to put it
Put the file in ComfyUI/models/diffusion_models/ (portable version: ComfyUI_windows_portable/ComfyUI/models/diffusion_models/). Older guides say models/unet: that folder still works. Press R in ComfyUI or restart it, then pick the file in Load Diffusion Model (UNETLoader). Not for Mac: FP8 and INT8 files do not load on Apple Silicon.
If a workflow says “Value not in list” for that node, the workflow expects a file with another name. Click the node and choose this one.
Which graphics cards it fits
| VRAM | This file | Best file for that card (RTX 40/50) | |
|---|---|---|---|
| 6 GB | Runs well | Fits in VRAM, 0.5 GB to spare | this file |
| 8 GB | Runs well | Fits in VRAM, 2.5 GB to spare | Illustrious-XL-v0.1.safetensors (6.9 GB) |
| 10 GB | Runs well | Fits in VRAM, 4.5 GB to spare | Illustrious-XL-v0.1.safetensors (6.9 GB) |
| 12 GB | Runs well | Fits in VRAM, 6.5 GB to spare | Illustrious-XL-v0.1.safetensors (6.9 GB) |
| 16 GB | Runs well | Fits in VRAM, 10.5 GB to spare | Illustrious-XL-v0.1.safetensors (6.9 GB) |
| 20 GB | Runs well | Fits in VRAM, 14.5 GB to spare | Illustrious-XL-v0.1.safetensors (6.9 GB) |
| 24 GB | Runs well | Fits in VRAM, 18.5 GB to spare | Illustrious-XL-v0.1.safetensors (6.9 GB) |
| 32 GB | Runs well | Fits in VRAM, 26.5 GB to spare | Illustrious-XL-v0.1.safetensors (6.9 GB) |
| 48 GB | Runs well | Fits in VRAM, 42.5 GB to spare | Illustrious-XL-v0.1.safetensors (6.9 GB) |
Need = file × 1 + 1.2 GB for the picture and 0.8 GB for Windows and the browser — the same rule as the rest of the site. FP8 files do not load on a Mac (Apple Silicon); use a 16-bit or GGUF file there.
What else you need
This file alone does not make a picture. With it you load:
| Role | File | Size | Folder |
|---|---|---|---|
| Model | illustrious_fp8_e4m3fn.safetensors | 3.5 GB | models/diffusion_models |
3.5 GB in total. Smaller text-encoder versions and other options are on the Illustrious / Pony page.
Other files of Illustrious / Pony
| File | Precision | Size | VRAM to fit |
|---|---|---|---|
| Illustrious-XL-v0.1.safetensors | 16-bit | 6.9 GB | 7.1 GB |
| illustrious_fp8_e4m3fn.safetensors | FP8 | 3.5 GB | 5.5 GB |
| illustrious-q8_0.gguf | Q8_0 | 2.7 GB | 4.7 GB |
| illustrious-q6_k.gguf | Q6_K | 2.1 GB | 4.1 GB |
| illustrious-q5_k_m.gguf | Q5_K_M | 1.8 GB | 3.8 GB |
| illustrious-q4_k_m.gguf | Q4_K_M | 1.5 GB | 3.5 GB |
| illustrious-q3_k_m.gguf | Q3_K_M | 1.2 GB | 3.2 GB |
| illustrious-q2_k.gguf | Q2_K | 0.9 GB | 2.9 GB |
Same model, different compression. 8-bit files (FP8, INT8, Q8_0) look almost the same as 16-bit; below Q5 the loss starts to show.
Want the answer for your exact card? Check your GPU. Every file of every model: ComfyUI model files.
Size and source read from Hugging Face (2026-10-01).