Cyberax AI Playbook
cyberax.com
Model · Stability AI · Image-Gen

Stable Diffusion 3.5

Stability AI's open image-gen family. Three sizes (Large, Large Turbo, Medium) — runs locally on consumer GPUs and supports a massive ecosystem of LoRAs and ControlNets.

Modality
Image-Gen
License
Stability AI Community License (Open weights)
Released
October 22, 2024
Last verified
October 28, 2026
Runs locally
Yes

What you need to run it

Mac
Yes. Any Apple Silicon Mac (M1 or newer) with at least 16 GB (32 GB recommended) of memory. Newer chips are faster, but memory is what decides whether it runs.
Windows / Linux PC
NVIDIA works best. A graphics card with at least 12 GB (24 GB recommended) of video memory.
No graphics card
Not practical. Too slow without a graphics card or Apple Silicon.

The smaller Medium tier suits a 16 GB Mac; Large wants 32 GB, and common Mac apps such as Draw Things and DiffusionKit can run the family.

Numbers are for: Medium (2.5B) for the minimum; Large (8B) for recommended. Our estimate from the model’s size — the maker publishes no figure.

Strengths

  • Open weights — fully self-hostable
  • Largest community ecosystem (ComfyUI, A1111, LoRAs, ControlNets)
  • Three size tiers for different hardware budgets

Weaknesses

  • Quality below FLUX.1 [pro] at the very high end
  • Community License has revenue thresholds for commercial use

Try it

WhereTypeNotes
Hugging Face weights Stability Community License
ComfyUI local Reference local UI
Stable Assistant product Hosted offering

Change log

  • — Added hardware requirements (Mac support, memory, NVIDIA). Source: an estimate from the model sizes (Medium about 2.5B, Large about 8B).
  • — Verified current against Stability's news page: its 2026 posts announce no Stable Diffusion image model after 3.5.
  • — Verified current. A full Hugging Face org enumeration by creation date shows no Stable Diffusion 4 repo, and Stability's own 2026 news page never mentions one — the widely circulated 'SD4, April 2026' claim is fabricated.
  • — Initial entry.