Stable Diffusion XL 1.0 on NVIDIA Grace Blackwell Ultra GB300
Yes — Grace Blackwell Ultra GB300 runs Stable Diffusion XL 1.0 excellently at FP16 — 18 tok/s. 288 GB VRAM with plenty of headroom.
Model Size
6.6B
Device VRAM
288 GB
Bandwidth
8000 GB/s
Quantization
FP16
Performance by Quantization
OwnRig currently has one published compatibility entry for Stable Diffusion XL 1.0 on NVIDIA Grace Blackwell Ultra GB300 at FP16. This is the best supported pairing we can stand behind today.
| Quantization | Speed | TTFT | Fits in VRAM | Rating | Confidence |
|---|---|---|---|---|---|
| FP16 | 18 tok/s | 80ms | ✓ Yes | Excellent | estimated |
Notes
FP16
Full FP16 quality. 282GB headroom enables massive batch sizes.
About Stable Diffusion XL 1.0
Stable Diffusion XL 1.0 (6.6B) is a image gen model. The standard for local image generation. 1024x1024 base resolution. Massive LoRA/checkpoint ecosystem. Runs well on 8GB+ VRAM. VRAM usage varies by resolution and batch size; 6.5GB is for single 1024x1024 generation.
View all Stable Diffusion XL 1.0 hardware options →About NVIDIA Grace Blackwell Ultra GB300
NVIDIA Grace Blackwell Ultra GB300 has 288 GB at 8000 GB/s. Street price: $30,000.
See all models NVIDIA Grace Blackwell Ultra GB300 can run →Estimate method: Estimated from GB300 bandwidth ratio vs RTX 4090. Reference hardware source: dell.com (2026-03-23)
Performance varies by driver version, inference engine, quantization method, context length, and system configuration. Figures shown are estimates based on community benchmarks and may not reflect your exact setup. Product names are trademarks of their respective owners. OwnRig is independent and not affiliated with any hardware or AI model provider.