Stable Diffusion XL
40 consumer GPUs can run Stable Diffusion XL at Q4 natively. Precise VRAM thresholds and benchmarks below.
llama.cpp 0.2.x · CUDA 12 · ROCm 6 · Updated monthly · methodology →
Execution Context
This model requires a Entry GPU (8 GB VRAM)
Cómo ejecutar este modelo
Check if your GPU can run Stable Diffusion XL →
VRAM Calculator — instant compatibility check
RTX 5090
32 GB · Runs Q4 natively · Check availability
*Prices and availability may change. Some links are affiliate links.
System Requirements
VRAM by Quantization
| Quantization | VRAM needed | Disk space | Quality |
|---|---|---|---|
| FP16 (max quality) | 12 GB | 13 GB | Maximum |
| Q8 (high quality) | 8 GB | 7 GB | Near-lossless |
| Q4 (recommended) Best balance | 6 GB | 4 GB | Recommended |
| Q2 (minimum) | 4 GB | 2.5 GB | Quality loss |
Model Details
| Developer | Stability AI |
| Parameters | 6.6B |
| License | CreativeML Open RAIL++-M |
| Use cases | image |
| Released | 2023-07 |
Hugging Face
stabilityai/stable-diffusion-xl-base-1.0 Can your GPU run Stable Diffusion XL?
Stable Diffusion XL requires 6 GB VRAM at Q4. 40 consumer GPUs meet this threshold. Below 8 GB or 4 GB you'll hit significant offload latency.
Hardware Performance Matrix
40 Q4 native · 0 offload · 0 unsupported
| GPU Unit | VRAM | Compatibility | Est. Speed | Action |
|---|---|---|---|---|
| RTX 5090 | 32GB | Optimal | 160 tok/s | Calculate → |
| RTX 4090 | 24GB | Optimal | 106 tok/s | Calculate → |
| M4 Ultra | 128GB | Optimal | 119 tok/s | Calculate → |
| RTX 5080 | 16GB | Optimal | 99 tok/s | Calculate → |
| M3 Ultra | 192GB | Optimal | 102 tok/s | Calculate → |
| RTX 4080 Super | 16GB | Optimal | 80 tok/s | Calculate → |
| RTX 5070 Ti | 16GB | Optimal | 86 tok/s | Calculate → |
| RTX 3090 | 24GB | Optimal | 78 tok/s | Calculate → |
| M4 Max 48GB | 48GB | Optimal | 69 tok/s | Calculate → |
| RX 7900 XTX | 24GB | Optimal | 92 tok/s | Calculate → |
| M4 Max 36GB | 36GB | Optimal | 67 tok/s | Calculate → |
| RTX 4070 Ti Super | 16GB | Optimal | 68 tok/s | Calculate → |
| RTX 3080 Ti | 12GB | Optimal | 72 tok/s | Calculate → |
| RX 7900 XT | 20GB | Optimal | 75 tok/s | Calculate → |
| RTX 5070 | 12GB | Optimal | 66 tok/s | Calculate → |
| RTX 3080 | 10GB | Optimal | 57 tok/s | Calculate → |
| M4 Pro | 24GB | Optimal | 46 tok/s | Calculate → |
| RX 7800 XT | 16GB | Optimal | 56 tok/s | Calculate → |
| RX 6800 XT | 16GB | Optimal | 40 tok/s | Calculate → |
| RTX 4070 | 12GB | Optimal | 47 tok/s | Calculate → |
| RTX 4060 Ti 16GB | 16GB | Optimal | 38 tok/s | Calculate → |
| RX 7700 XT | 12GB | Optimal | 36 tok/s | Calculate → |
| RTX 3070 Ti | 8GB | Optimal | 51 tok/s | Calculate → |
| RTX 4060 Ti | 8GB | Optimal | 38 tok/s | Calculate → |
| RTX 3070 | 8GB | Optimal | 40 tok/s | Calculate → |
| RX 6700 XT | 12GB | Optimal | 28 tok/s | Calculate → |
| M3 Pro | 18GB | Optimal | 32 tok/s | Calculate → |
| RTX 3060 Ti | 8GB | Optimal | 38 tok/s | Calculate → |
| RTX 2080 Ti | 11GB | Optimal | 39 tok/s | Calculate → |
| RTX 3060 | 12GB | Optimal | 35 tok/s | Calculate → |
| M2 Pro | 16GB | Optimal | 29 tok/s | Calculate → |
| RTX 4060 | 8GB | Optimal | 29 tok/s | Calculate → |
| Arc A770 16GB | 16GB | Optimal | 22 tok/s | Calculate → |
| M1 Pro | 16GB | Optimal | 24 tok/s | Calculate → |
| RX 7600 | 8GB | Optimal | 26 tok/s | Calculate → |
| RX 6600 XT | 8GB | Optimal | 25 tok/s | Calculate → |
| Arc A750 8GB | 8GB | Optimal | 19 tok/s | Calculate → |
| RX 6600 | 8GB | Optimal | 21 tok/s | Calculate → |
| RTX 3050 8GB | 8GB | Optimal | 19 tok/s | Calculate → |
| GTX 1660 Super | 6GB | Optimal | 25 tok/s | Calculate → |
Recommended GPUs for Stable Diffusion XL
Best picks by compatibility, VRAM headroom, and value — prices and availability may change.
RTX 5090
32 GB VRAM
Check availability →
RTX 4090
24 GB VRAM
Check availability →
M4 Ultra
128 GB VRAM
Check availability →
Some links are Amazon affiliate links. We may earn a commission at no extra cost to you. Amazon cookies may last up to 24 hours after your click.
Stable Diffusion XL — Compatibility guide
A lightweight model like Stable Diffusion XL runs well on consumer hardware from 6 GB VRAM. Ideal for daily use with Ollama or LM Studio. Use the VRAM calculator to check your setup.
Compare GPUs for Stable Diffusion XL
Which GPU is worth it? Real specs and benchmarks side by side.
Compatible Hardware
GPUs that run Stable Diffusion XL at Q4 — sorted by AI performance score.
Some links are Amazon affiliate links. We may earn a commission at no extra cost to you. Amazon cookies may last up to 24 hours after your click.
More Practical Alternatives
Similar models in the image category with comparable VRAM footprints.
Stable Diffusion 3.5 Large
8B params • 10GB VRAM
Stability AI • Stability AI Community
Stable Diffusion 3 Medium
2B params • 3GB VRAM
Stability AI • Stability AI Community
Stable Diffusion 3.5 Medium
2B params • 5GB VRAM
Stability AI • Stability AI Community
Flux.1 Dev
12B params • 12GB VRAM
Black Forest Labs • FLUX.1-dev Non-Commercial
Not sure which GPU you need for Stable Diffusion XL?
The VRAM Calculator tells you exactly which quantization your hardware can handle.