Skip to content

Best GPU for Stable Diffusion XL 1.0: VRAM Requirements

Stable Diffusion XL 1.0 needs about 7.7 GB of GPU memory in BF16 and 1.9 GB at 4 bits. See which GPUs fit it for inference and fine-tuning.

Stable Diffusion XL 1.0 needs about 7.7 GB of VRAM in FP16, 3.9 GB in FP8 and 1.9 GB at 4 bits for inference. In FP16 it fits on one NVIDIA GeForce RTX 5080 16GB.

Stable Diffusion XL 1.0 is a 3.5B-parameter image generation model from Stability AI, released in July 2023 and published under the CreativeML Open RAIL++-M. Its weights alone take 7 GB in BF16 and 1.8 GB at 4 bits per parameter; the tables below add runtime memory and fine-tuning, then list the GPUs that hold each setup.

Recommended GPUs for Stable Diffusion XL 1.0

Stable Diffusion XL 1.0 VRAM requirements by precision

Model weights plus a 10 % margin for activations and runtime buffers, at one request.

PrecisionWeightsKV cacheTotal for inference
BF16 / FP167 GBNot applicable7.7 GB
FP83.5 GBNot applicable3.9 GB
INT41.8 GBNot applicable1.9 GB

Stable Diffusion XL 1.0 VRAM by task

Fine-tuning rows assume a short sequence, batch 1 and gradient checkpointing; longer sequences add activation memory.

TaskGPU memory
QLoRA (4-bit base)2.3 GB
LoRA (BF16 base)9.1 GB
Full fine-tuning (BF16, AdamW)61.6 GB

GPUs that fit Stable Diffusion XL 1.0

Number of cards whose combined memory holds each setup, assuming the model is split across them with tensor or pipeline parallelism. A dash means more than eight cards.

GPUMemoryBF16 inference (7.7 GB)FP8 inference (3.9 GB)INT4 inference (1.9 GB)QLoRA (2.3 GB)LoRA (9.1 GB)
NVIDIA GeForce RTX 5080 16GB16 GB1 GPU1 GPU1 GPU1 GPU1 GPU
NVIDIA GeForce RTX 4090 24GB24 GB1 GPU1 GPU1 GPU1 GPU1 GPU
NVIDIA L4 24GB24 GB1 GPU1 GPU1 GPU1 GPU1 GPU
NVIDIA GeForce RTX 5090 32GB32 GB1 GPU1 GPU1 GPU1 GPU1 GPU
NVIDIA Tesla V100 32GB32 GB1 GPU1 GPU1 GPU1 GPU1 GPU
NVIDIA A100 PCIe 40GB40 GB1 GPU1 GPU1 GPU1 GPU1 GPU
NVIDIA L40S 48GB48 GB1 GPU1 GPU1 GPU1 GPU1 GPU
NVIDIA Quadro RTX 8000 48GB48 GB1 GPU1 GPU1 GPU1 GPU1 GPU
NVIDIA RTX 6000 Ada 48GB48 GB1 GPU1 GPU1 GPU1 GPU1 GPU
NVIDIA RTX A6000 48GB48 GB1 GPU1 GPU1 GPU1 GPU1 GPU
NVIDIA A100 PCIe 80GB80 GB1 GPU1 GPU1 GPU1 GPU1 GPU
NVIDIA A100 SXM 80GB80 GB1 GPU1 GPU1 GPU1 GPU1 GPU
NVIDIA H100 PCIe 80GB80 GB1 GPU1 GPU1 GPU1 GPU1 GPU
NVIDIA H100 SXM 80GB80 GB1 GPU1 GPU1 GPU1 GPU1 GPU
NVIDIA RTX PRO 6000 Blackwell 96GB96 GB1 GPU1 GPU1 GPU1 GPU1 GPU
NVIDIA H200 141GB141 GB1 GPU1 GPU1 GPU1 GPU1 GPU
NVIDIA B200 180GB180 GB1 GPU1 GPU1 GPU1 GPU1 GPU
NVIDIA B300 288GB288 GB1 GPU1 GPU1 GPU1 GPU1 GPU
NVIDIA GB300 NVL288 GB1 GPU1 GPU1 GPU1 GPU1 GPU

What is Stable Diffusion XL 1.0?

Stable Diffusion XL 1.0 is a latent diffusion model for text-to-image generation at 1024 × 1024 pixels, with a 2.6-billion-parameter UNet and two text encoders. Its large ecosystem of LoRA adapters and ControlNets keeps it widely used for image pipelines.

Developer
Stability AI
Released
July 2023
Parameters
3.5B
License
CreativeML Open RAIL++-M

About 3.5 billion parameters for the base pipeline (UNet, both text encoders and VAE); the optional refiner adds its own weights.

Source: Stable Diffusion XL base 1.0 model card (as of November 17, 2026).

Frequently asked questions

How much VRAM does Stable Diffusion XL 1.0 need?
For inference, Stable Diffusion XL 1.0 needs about 7.7 GB in BF16, 3.9 GB in FP8, 1.9 GB in INT4, including a 10 % runtime margin. Real usage depends on the inference engine and its settings.
Can Stable Diffusion XL 1.0 run on a single GPU?
Yes. In BF16 it needs about 7.7 GB, which fits one NVIDIA GeForce RTX 5080 16GB (16 GB).
How much GPU memory does fine-tuning Stable Diffusion XL 1.0 take?
QLoRA (4-bit base): about 2.3 GB; LoRA (BF16 base): about 9.1 GB; Full fine-tuning (BF16, AdamW): about 61.6 GB. Longer training sequences and larger batches add activation memory on top.
What is the best GPU for Stable Diffusion XL 1.0?
Best for inference: 1 GPU × NVIDIA L4 24GB (FP8 or INT8 weights, 3.9 GB). Best for fine-tuning: 1 GPU × NVIDIA L4 24GB (LoRA on BF16 weights, 9.1 GB). Budget pick: 1 GPU × NVIDIA GeForce RTX 5080 16GB (Smallest card class that holds a 4-bit build, 1.9 GB). Check live offers before booking, as availability changes.
Can Stable Diffusion XL 1.0 run on an RTX 4090?
Yes. In FP16 it needs about 7.7 GB, which fits one RTX 4090 (24 GB).
Can Stable Diffusion XL 1.0 run on an RTX 5090?
Yes. In FP16 it needs about 7.7 GB, which fits one RTX 5090 (32 GB).

Estimates use the formulas of the LLM VRAM calculator (decimal GB). Real usage depends on the inference engine, quantization format and memory fragmentation: test on the target GPU before a long rental.

Explore the live market

Every offer on the live market comes from a reviewed supplier and is sold by EverXCloud Inc.