Can the RTX 4090 24 GB run Illustrious XL / Pony (SDXL anime)?
Yes. 16-bit fits on the RTX 4090 24 GB with 16.9 GB to spare.
16-bit (6.9 GB) needs about 7.1 GB in use, so 16.9 GB of the 24 GB stays free: room for a larger image, a LoRA or a ControlNet.
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Checkpoint | Illustrious-XL-v0.1.safetensors 16-bit · OnomaAIResearch/Illustrious-xl-early-release-v0 | models/checkpoints | 6.9 GB | Download → |
| Total download · keep about the same free on disk | 6.9 GB | |||
One file: the checkpoint already contains the text encoders and the VAE. Sizes from Hugging Face, 2026-10-01.
02Every Illustrious / Pony file on 24 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit ← SAFETENSORS · OnomaAIResearch | 6.9 GB | 7.1 GB | fits · 16.9 GB spare | the original weights | Hugging Face → |
| FP8 SAFETENSORS · calcuis | 3.5 GB | 5.5 GB | fits · 18.5 GB spare | practically identical to the original | Hugging Face → |
| Q8_0 GGUF · calcuis | 2.7 GB | 4.7 GB | fits · 19.3 GB spare | practically identical to the original | Hugging Face → |
| Q6_K GGUF · calcuis | 2.1 GB | 4.1 GB | fits · 19.9 GB spare | very close to the original | Hugging Face → |
| Q5_K_M GGUF · calcuis | 1.8 GB | 3.8 GB | fits · 20.2 GB spare | close; small differences in fine detail | Hugging Face → |
| Q4_K_M GGUF · calcuis | 1.5 GB | 3.5 GB | fits · 20.5 GB spare | good; some loss in fine detail and text | Hugging Face → |
| Q3_K_M GGUF · calcuis | 1.2 GB | 3.2 GB | fits · 20.8 GB spare | noticeable loss of detail | Hugging Face → |
| Q2_K GGUF · calcuis | 0.9 GB | 2.9 GB | fits · 21.1 GB spare | heavy loss; a last resort | Hugging Face → |
“Needed” adds 1.2 GB of working memory for Illustrious / Pony and a 0.8 GB reserve. Sizes 2026-10-01. The 6.94 GB checkpoint holds the UNet plus text encoders and VAE; only the UNet (about 5.1 GB) sits in VRAM while sampling. The GGUF and FP8 files from calcuis contain the UNet only.
03The text encoder
The text encoder is inside the checkpoint, so there is nothing extra to download.
04Measured and reported results
| Label | Setup | Result | Peak VRAM | Date | Source |
|---|---|---|---|---|---|
| reported | Illustrious-XL-v2.0 · 1024x1024 “NVIDIA RTX 4090 | 7.00it/s | 0.14s/it | CUDA 12.9 | ComfyUI (Unknown) | Windows 11 24H2” Community speed list; ComfyUI, Euler/Normal, CFG 8, square 1:1, batch speed only (no per-image time); date = list last-updated date; SDXL 1024px section | 0.14 s/it | — | 2025-11-29 | huggingface.co → |
Other people's numbers are copied as published, with a link. Send yours.
05About the RTX 4090 24 GB
The RTX 4090 24 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.)
24 GB GDDR6X · 384-bit · 1008 GB/s · Ada Lovelace. Everything that runs on it →
06Questions
How much VRAM does Illustrious / Pony need?
Around 2.9 GB with the smallest file (Q2_K) and 5.5 GB with an 8-bit file (FP8). The full 16-bit file needs about 7.1 GB.
Which Illustrious / Pony file should I download for the RTX 4090 24 GB?
16-bit (6.9 GB) from OnomaAIResearch/Illustrious-xl-early-release-v0.
FP8 or Q8_0 for Illustrious / Pony on the RTX 4090 24 GB?
FP8 (3.5 GB): the RTX 4090 24 GB computes it natively, while Q8_0 (2.7 GB) is unpacked on the fly.
How much do I need to download for Illustrious / Pony on the RTX 4090 24 GB?
6.9 GB: Illustrious-XL-v0.1.safetensors.