What GPU do I need to run stabilityai/stable-diffusion-3.5-medium?
2.5B parameters, published in BF16. View on Hugging FaceGated
Set up stable-diffusion-3.5-mediumstable-diffusion-3.5-medium is published by stabilityai on Hugging Face, with 138,147 downloads and 1,061 likes to date. It's a unlisted-architecture model built for text-to-image, published natively in BF16, and gated: you'll need to accept the model's terms on Hugging Face before downloading weights.
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision, plus a fixed overhead for activation memory and allocator fragmentation. Diffusion and video models carry no KV-cache. The real driver of extra memory is output resolution and frame count, which this flat overhead does not model. Full formula and assumptions: methodology.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 4.6 GB | 5.5 GB | RTX 4070 Super | 1 | $0.121/hr |
| FP8 (quantized) | 2.3 GB | 2.8 GB | RTX 4070 Super | 1 | $0.121/hr |
| INT4 (quantized) | 1.2 GB | 1.4 GB | RTX 4070 Super | 1 | $0.121/hr |
A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.
INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run stable-diffusion-3.5-medium at its published (BF16) precision: 1× RTX 4070 Super, at $0.121/hr per GPU ($0.121/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
stable-diffusion-3.5-medium: common questions
How much VRAM does stable-diffusion-3.5-medium need?
5.5 GB at BF16, 2.8 GB at FP8 (quantized), 1.4 GB at INT4 (quantized). All of those sit under 6 GB, the smallest capacity this page reasons about, so VRAM is not what limits where this model runs. The 4.6 GB of weights plus inference overhead is the whole requirement.
Do I need approval to download stable-diffusion-3.5-medium?
Yes. stabilityai gates this repository on Hugging Face, so you have to accept its terms with a signed-in account before the weights will download. It does not change the 5.5 GB the model needs once you have them.
How many copies of stable-diffusion-3.5-medium fit on one RTX 4070 Super?
2, by VRAM alone. That card carries 12.0 GB and one copy needs 5.5 GB at BF16, on a live rate of $0.121/hr for the whole card. Throughput is not modelled here, so 2 copies is not 2 times the requests served.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More Stable Diffusion 3 models
- stable-diffusion-3-medium-diffusers (2.1B, F16)
- stable-diffusion-3.5-large (8.1B, BF16)
Alternatives at this size
Other models for text-to-image within about a third of stable-diffusion-3.5-medium's 2.5B parameters, from other model lines.
- RealVisXL_V5.0 (2.6B, F32)
- playground-v2.5-1024px-aesthetic (2.6B, F32)
- NSFW-GEN-ANIME-v2 (2.6B, F32)
- LUSTIFY-v2.0 (2.6B, F32)
- LUSTIFY-v2.0 (2.6B, F32)
More on stable-diffusion-3.5-medium
Fits on an 8 GB GPU at BF16: every model that fits in 8 GB.
Best image generation models: how stable-diffusion-3.5-medium ranks against the rest.
Compare stable-diffusion-3.5-medium with FLUX.1-dev, FLUX.1-schnell, Qwen-Image, Qwen-Image-2.1, Qwen-Image-2512.
Related reading: H100 pricing and specs, Fast diffusion inference on GPU VMs, and What AI inference is.
