stable-diffusion-3.5-large
stabilityai/stable-diffusion-3.5-large
Official · BF16 · safetensors
Runtime certified: Diffusers
| Precision / quantization | Format | Bits | Publisher trust | Deployment state |
|---|---|---|---|---|
| BF16 | safetensors | 16 | Official | Runtime certified |
Stable Diffusion · General · Stable Diffusion 3.5
Stable Diffusion 3.5 Large: Specs, GPU requirements, hosting & deployment
Stable Diffusion 3.5 Large is a current Image Generation release in the Stable Diffusion family, certified from its immutable official source revision.
Total parameters8.1B
Active parametersN/A / Not directly comparable
Context windowN/A / Not directly comparable
Release statusCurrent · Current
ArchitectureMultimodal diffusion transformer
ModalitiesText, Image
LicenseStability AI Community License
Deployment stateDeployable with certified configuration
Commercial stateCommercial Use Allowed With Conditions
Release date2024-10-22
Architecture, strengths and use cases
Stable Diffusion 3.5 Large is an official self-hostable Stability AI Image generation release. It uses Multimodal diffusion transformer with 8.146B. Exact checkpoint, license, runtime, and hardware evidence is tied to the verified upstream revision.
Stable Diffusion 3.5 Large uses Multimodal diffusion transformer with 8.146B. Pipeline and configuration fields are reported only where the official source publishes them.
Verified Multimodal diffusion transformer architecture
Official checkpoint and pipeline evidence
Official BF16 checkpoint coverage
Self-hosted Image generation workloads
Controlled model evaluation
Production deployment planning
Certified checkpoints and quantizations
Only exact, source-certified variants attached to this release are shown.
Recommended hardware
Use only the listed runtime configurations with the exact checkpoint precision. Hardware sizing considers resident pipeline memory, runtime overhead, input and output dimensions, batch size, and safety headroom.
Estimated weight memory15.63 GB
Runtime overhead12.25 GB
Total with safety margin34.57 GB
Recommended best value
1× NVIDIA H200 SXM 141GB
141 GB total VRAM · nvswitch
106.43 GB headroom · Limited capacity
USD 2,345 / monthLowest-cost viable
2× NVIDIA L4 24GB
48 GB total VRAM · pcie
13.43 GB headroom · Available
USD 500 / monthHighest performance
1× NVIDIA H200 SXM 141GB
141 GB total VRAM · nvswitch
106.43 GB headroom · Limited capacity
USD 2,345 / monthLicense and self-hosting considerations
The exact pipeline and selected precision must fit on the chosen GPUs. Requirements vary with resolution, duration, batch size, modalities, and runtime; language-model KV-cache rules are not applied.
Stable Diffusion 3.5 Large is published under Stability AI Community License. The release-scoped official license link and verification date are retained with the catalogue record.
Commercial Use Allowed With Conditions. Commercial use is conditional. Review the linked official terms before deployment.
Alternatives and sibling variants
Stable Diffusion 3.5 Medium, Stable Diffusion 3.5 Large Turbo
Release timeline
stability-ai/stable-diffusion/stable-diffusion-3-5-large @ 03fe2a9cc668c7112e3999dc872017027c715629bf138cb14bd0d30548b4c1f0
Frequently asked questions
How much VRAM does Stable Diffusion 3.5 Large require?
The estimate uses the certified checkpoint, precision, runtime, workload dimensions, batch size, and domain-specific overhead.
Which runtimes support Stable Diffusion 3.5 Large?
Certified upstream runtime evidence is available for diffusers.
Can Stable Diffusion 3.5 Large be used commercially?
The stored commercial classification is Commercial Use Allowed With Conditions. Consult the official Stability AI Community License terms for the final obligations.
Official references
Last verified: 2026-08-26