Can you run Stable Diffusion XL 1.0 locally?

Stable Diffusion family · July 2023 · 3.5B parameters · Hugging Face model card

How much VRAM does Stable Diffusion XL 1.0 need at each quantization?

Stable Diffusion XL 1.0 needs 3.8 GB of VRAM at Q4_K_M. The table below lists weights-only size and total VRAM including overhead for each common quantization level including runtime overhead.

Latent diffusion UNet — no KV cache. Table adds a 1.5 GB activation overhead for 1024×1024 generation; the 6.9 GB FP16 checkpoint matches the 3.5B total (UNet 2.6B + two text encoders + VAE).

Method: weights = parameters × bits-per-weight (Q4_K_M ≈ 4.8, Q5_K_M ≈ 5.7, Q6_K ≈ 6.6, Q8_0 ≈ 8.5, FP16 = 16), plus 10% loading overhead, plus KV cache from the verified architecture config (not applicable to this architecture). Source: 3.5B-parameter base model (2.6B UNet + CLIP-L + OpenCLIP-G text encoders + VAE), 6.9 GB FP16 checkpoint — HF model card (stabilityai/stable-diffusion-xl-base-1.0).

Which GPUs can run Stable Diffusion XL 1.0 locally?

At Q4_K_M with a 4k context, Stable Diffusion XL 1.0 needs 3.8 GB of VRAM. The lists below are computed live from our GPU database and grouped by how much headroom the card has. Disclosure: CompareAIHardware.com participates in the Amazon Associates program and earns from qualifying purchases through links on this page. Affiliate relationships do not influence our recommendations.

Runs Stable Diffusion XL 1.0 comfortably (25%+ VRAM headroom)

Minimum GPUs that fit Stable Diffusion XL 1.0 at Q4_K_M

These GPUs hold the model but leave little headroom — keep contexts short.

Can a Mac run Stable Diffusion XL 1.0?

Yes — these Apple Silicon machines fit Stable Diffusion XL 1.0 at Q4_K_M, since macOS lets the GPU use about 75% of unified memory. Generation speed is bound by memory bandwidth, so the GB/s column matters as much as capacity.

Can Stable Diffusion XL 1.0 run on mini PCs, Jetson, or NPU devices?

These edge and NPU devices from our database have enough memory for Stable Diffusion XL 1.0 at Q4_K_M. Their memory bandwidth is far below discrete GPUs, so expect a fraction of desktop generation speed.

Which pre-built systems can run Stable Diffusion XL 1.0?

These mini PCs and workstations from our database fit Stable Diffusion XL 1.0 at Q4_K_M. Usable-memory figures are conservative: Windows shares about half of system RAM with the GPU by default (Linux can expose more), macOS lets Apple Silicon GPUs use about 75% of unified memory, and Linux unified-memory systems such as GB10 expose roughly 90%. Generation speed is bound by memory bandwidth, so compare the GB/s column before buying.

Frequently asked questions

Related guides

• Open Stable Diffusion XL 1.0 in the VRAM calculator — pick quantization and context, see the memory math per GPU class.
• Best GPU for Stable Diffusion
• Best Laptops for Stable Diffusion
• Best GPU Under $500