Datasheet for local AI49 models98 GPUsData read 2026-09-25
No adsNo tracking
Check my GPU →

Can the RX 9070 XT 16 GB run Illustrious XL / Pony (SDXL anime)?

Image model · 3.5B16 GB GDDR6 · 256-bit · 640 GB/s · RDNA 4Data 2026-09-25
Runs well
Yes — and comfortably.

Download 16-bit (6.9 GB). With the model's working memory it needs about 7.1 GB, leaving 8.9 GB spare on 16 GB. Quality: the original weights.

Best file16-bit
File size6.9 GB
VRAM needed~7.1 GB
System RAM16 GB+
Memory map · RX 9070 XT 16 GB7.1 GB / 16 GB
08 GB16 GB
Weights 16-bit · 5.1 GBWorking memory · 1.2 GBReserve · 0.8 GBFree · 8.9 GB
calculated from real file sizes plus working memory. Not yet measured on this setup. How this works.

01What to download

PartFileFolderSize
CheckpointIllustrious-XL-v0.1.safetensors
16-bit · OnomaAIResearch/Illustrious-xl-early-release-v0
models/checkpoints6.9 GBDownload →
Total download · keep about the same free on disk6.9 GB

One file: the checkpoint already contains the text encoders and the VAE. 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: 16 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 6.9 GB, plus roughly 6 GB for Windows, ComfyUI and a browser: 12.9 GB in total. With less RAM it still runs, but Windows starts swapping to disk and loading gets very slow. calculated

02Every Illustrious / Pony file on 16 GB

FileSizeNeededOn this cardQualityDownload
16-bit ←
SAFETENSORS · OnomaAIResearch
6.9 GB7.1 GBfits · 8.9 GB sparethe original weightsHugging Face →
FP8
SAFETENSORS · calcuis
3.5 GB5.5 GBfits · 10.5 GB sparepractically identical to the originalHugging Face →
Q8_0
GGUF · calcuis
2.7 GB4.7 GBfits · 11.3 GB sparepractically identical to the originalHugging Face →
Q6_K
GGUF · calcuis
2.1 GB4.1 GBfits · 11.9 GB sparevery close to the originalHugging Face →
Q5_K_M
GGUF · calcuis
1.8 GB3.8 GBfits · 12.2 GB spareclose; small differences in fine detailHugging Face →
Q4_K_M
GGUF · calcuis
1.5 GB3.5 GBfits · 12.5 GB sparegood; some loss in fine detail and textHugging Face →
Q3_K_M
GGUF · calcuis
1.2 GB3.2 GBfits · 12.8 GB sparenoticeable loss of detailHugging Face →
Q2_K
GGUF · calcuis
0.9 GB2.9 GBfits · 13.1 GB spareheavy loss; a last resortHugging Face →

Sizes from the Hugging Face file listing, read 2026-09-25. “Needed” = file + 1.2 GB working memory for this model + 0.8 GB kept free for the system. 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.

04About this GPU

ComfyUI supports AMD GPUs on Windows officially since v0.7.0 (January 2026), through ROCm. Memory works the same as on NVIDIA, so the fit verdicts apply. Some custom nodes are NVIDIA-only. RX 9000 (RDNA 4) GPUs have FP8 hardware, and ComfyUI computes FP8 natively on them with PyTorch 2.7+ and ROCm 6.4+.

RX 9070 XT 16 GB: 16 GB GDDR6 · 256-bit · 640 GB/s · RDNA 4. Everything that runs on the RX 9070 XT 16 GB →

05What more VRAM would change

Nothing to gain for this model: the RX 9070 XT 16 GB already runs a top-quality file entirely in VRAM. More memory would only help with bigger images, longer clips or several models at once.

06Measured and reported results

Nobody has sent measured numbers for this pair yet. If you run Illustrious / Pony on a RX 9070 XT 16 GB, send your time per image and peak VRAM and it will appear here, credited.

07Questions

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), counting working memory and a small system reserve. The full 16-bit file needs about 7.1 GB.

Which Illustrious / Pony file should I download for the RX 9070 XT 16 GB?

16-bit (6.9 GB) from OnomaAIResearch/Illustrious-xl-early-release-v0.

Is FP8 faster than GGUF on the RX 9070 XT 16 GB?

It can be. This GPU has FP8 hardware, and ComfyUI computes FP8 natively for files made for it (Comfy-Org's fp8_scaled files), or for any FP8 file with the --fast fp8_matrix_mult option. GGUF files are unpacked on the fly, which costs some speed.

How much do I need to download for Illustrious / Pony on the RX 9070 XT 16 GB?

About 6.9 GB for the model file, text encoder and VAE listed on this page, and the same again free on disk. With a 16 GB card, 16 GB of system RAM or more is recommended.