stabilityai/stable-diffusion-xl-base-1.0
stabilityai/stable-diffusion-xl-base-1.0
SDXL base, 1024px image generation on 8-10GB VRAM.
Parameters
3.5B
Context
4K
Downloads
4.3M
Likes
8.3K
Architecture
β
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 16.2 GB RAM 32.0 Β· Disk 49.2 | 18.1 GB RAM 32.0 Β· Disk 75.2 | 21.3 GB RAM 32.0 Β· Disk 114.2 |
| FP88bit | 9.8 GB RAM 32.0 Β· Disk 44.1 | 11.4 GB RAM 32.0 Β· Disk 70.1 | 14.2 GB RAM 32.0 Β· Disk 109.1 |
| INT88bit | 9.8 GB RAM 32.0 Β· Disk 44.1 | 11.4 GB RAM 32.0 Β· Disk 70.1 | 14.2 GB RAM 32.0 Β· Disk 109.1 |
| AWQ4bit | 6.7 GB RAM 32.0 Β· Disk 41.6 | 8.1 GB RAM 32.0 Β· Disk 67.6 | 10.9 GB RAM 32.0 Β· Disk 106.6 |
| GPTQ4bit | 6.7 GB RAM 32.0 Β· Disk 41.7 | 8.1 GB RAM 32.0 Β· Disk 67.7 | 10.9 GB RAM 32.0 Β· Disk 106.7 |
| GGUF4bit | 6.8 GB RAM 32.0 Β· Disk 41.7 | 8.2 GB RAM 32.0 Β· Disk 67.7 | 11.0 GB RAM 32.0 Β· Disk 106.7 |
GPU Recommendations
1Γ RTX 3080 Ti
12 GB VRAM
β 20.4 img/min
Effective production throughput β 14.3 images/min
score 0.6753
1Γ Tesla V100
16 GB VRAM
β 0 img/min (N/A β benchmark unavailable)
Effective production throughput β 0 images/min
score 0.6242
8Γ RTX 5090
256 GB VRAM
β 501.6 img/min
Effective production throughput β 351.1 images/min
score 0.352
1Γ RTX 3080
10 GB VRAM
β 18 img/min
Effective production throughput β 12.6 images/min
score 0.6783
π¬ Community β real deployment experience
0 Articles Β· 0 Benchmarks
GPUs that fit (single card)
Tesla V100
16 GB VRAM
$39.1
/mo Β· vast
RTX 3080
10 GB VRAM
$55.0
/mo Β· vast
RTX 3080 Ti
12 GB VRAM
$60.0
/mo Β· vast
RTX 4070S Ti
16 GB VRAM
$68.9
/mo Β· vast
L4
24 GB VRAM
$76.2
/mo Β· vast