SDXL-Turbo
stabilityai/sdxl-turbo
SDXL Turbo, 1-step real-time generation.
Parameters
3.5B
Context
4K
Downloads
980K
Likes
2.8K
Architecture
sd
GPU Requirements
VRAM / RAM / disk estimates by quantization and usage scenario
| Quantization | Minimum | Recommended | Production |
|---|---|---|---|
| FP1616bit | 16.2 GB RAM 32.0 · Disk 49.2 | 18.1 GB RAM 32.0 · Disk 75.2 | 21.3 GB RAM 32.0 · Disk 114.2 |
| FP88bit | 9.8 GB RAM 32.0 · Disk 44.1 | 11.4 GB RAM 32.0 · Disk 70.1 | 14.2 GB RAM 32.0 · Disk 109.1 |
| INT88bit | 9.8 GB RAM 32.0 · Disk 44.1 | 11.4 GB RAM 32.0 · Disk 70.1 | 14.2 GB RAM 32.0 · Disk 109.1 |
| AWQ4bit | 6.7 GB RAM 32.0 · Disk 41.6 | 8.1 GB RAM 32.0 · Disk 67.6 | 10.9 GB RAM 32.0 · Disk 106.6 |
| GPTQ4bit | 6.7 GB RAM 32.0 · Disk 41.7 | 8.1 GB RAM 32.0 · Disk 67.7 | 10.9 GB RAM 32.0 · Disk 106.7 |
| GGUF4bit | 6.8 GB RAM 32.0 · Disk 41.7 | 8.2 GB RAM 32.0 · Disk 67.7 | 11.0 GB RAM 32.0 · Disk 106.7 |
GPU Recommendations
1× RTX 5080
16 GB VRAM
≈ 169.5 img/min
Effective production throughput ≈ 118.6 images/min
score 0.6298
1× Tesla V100
16 GB VRAM
≈ 0 img/min (N/A — benchmark unavailable)
Effective production throughput ≈ 0 images/min
score 0.6246
8× RTX 5090
256 GB VRAM
≈ 2508 img/min
Effective production throughput ≈ 1755.6 images/min
score 0.36
1× RTX 5070
12 GB VRAM
≈ 91.5 img/min
Effective production throughput ≈ 64.1 images/min
score 0.6736
💬 Community — real deployment experience
0 Articles · 0 Benchmarks
GPUs that fit (single card)
Tesla V100
16 GB VRAM
$21.1
/mo · vast
RTX 4070S Ti
16 GB VRAM
$49.5
/mo · vast
RTX 5070
12 GB VRAM
$58.7
/mo · vast
RTX 5070 Ti
16 GB VRAM
$62.0
/mo · vast
RTX 3090
24 GB VRAM
$78.7
/mo · vast