What GPU do I need to run stabilityai/stable-diffusion-3-medium-diffusers?
2.1B parameters, published in F16. View on Hugging FaceGated
Set up stable-diff…medium-diffusersstable-diffusion-3-medium-diffusers is published by stabilityai on Hugging Face, with 37,559 downloads and 466 likes to date. It's a unlisted-architecture model built for text-to-image, published natively in F16, 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) |
|---|---|---|---|---|---|
| FP16 | 3.9 GB | 4.7 GB | V100 | 1 | $0.088/hr |
| FP8 (quantized) | 1.9 GB | 2.3 GB | RTX 4070 Super | 1 | $0.121/hr |
| INT4 (quantized) | 1.0 GB | 1.2 GB | RTX 3060 | 1 | $0.110/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-medium-diffusers at its published (F16) precision: 1× V100, at $0.088/hr per GPU ($0.088/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-medium-diffusers: common questions
How much VRAM does stable-diffusion-3-medium-diffusers need?
4.7 GB at FP16, 2.3 GB at FP8 (quantized), 1.2 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 3.9 GB of weights plus inference overhead is the whole requirement.
Do I need approval to download stable-diffusion-3-medium-diffusers?
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 4.7 GB the model needs once you have them.
How many copies of stable-diffusion-3-medium-diffusers fit on one V100?
3, by VRAM alone. That card carries 16.0 GB and one copy needs 4.7 GB at FP16, on a live rate of $0.088/hr for the whole card. Throughput is not modelled here, so 3 copies is not 3 times the requests served.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More stabilityai models
- stable-diffusion-xl-base-1.0 (2.6B, F32)
- sdxl-turbo (2.6B, F32)
- sd-turbo (866M, F32)
- stable-video-diffusion-img2vid-xt (1.5B, F32)
- stable-diffusion-3.5-medium (2.5B, BF16)
- stable-diffusion-3.5-large (8.1B, BF16)
Related reading: V100 pricing and specs, and The best GPUs for AI, ranked.
