Stable Diffusion 3.5 Large GGUF files and Mac RAM
8.1 billion parameter MM-DiT text-to-image model with three text encoders, positioned for professional use at 1 megapixel. The Stability AI Community License requires registration for commercial use and ends above USD $1,000,000 annual revenue.
No published Mac run with a GGUF build yet. The smallest complete GGUF download is 16.36 GB; a download that fits in memory does not prove the model runs.
- Smallest Mac with a published run
- none yetunknown below
- Smallest complete download
- 16.36 GBQ4_0 GGUF
- Files read
- 2026-10-24Hugging Face
Stability AI Community License. Commercial use: restricted. Excluded territories: none listed. Commercial use requires registration with Stability AI. Licenses terminate above USD $1,000,000 in annual revenue until a separate license is requested.
This is Stable Diffusion 3.5 Large, not Large Turbo or Medium.
Get the weekly local AI newsletter
The Thursday ModelFit newsletter: new local models and what fits your machine.
For: MacBook Air M5 16 GB
You'll also get the weekly ModelFit email. By signing up you agree to our Privacy Policy. Unsubscribe from either email anytime, in one click.
Which exact GGUF files make a complete build?
Only builds with every required component and an exact probed file size are shown.
Q4_0 GGUF
gguf · Q4_0 · 16.36 GB completeMac routes: ComfyUI
| File | Component | Required | Download | Source |
|---|---|---|---|---|
sd3.5_large-Q4_0.ggufcity96/stable-diffusion-3.5-large-gguf | MM-DiT denoiserdit | Yes | 4.77 GB | Hugging FaceRead 2026-10-24 |
text_encoders/clip_l.safetensorsstabilityai/stable-diffusion-3.5-large | CLIP-L text encodertext_encoder | Yes | 0.25 GB | Hugging FaceRead 2026-10-24 |
text_encoders/clip_g.safetensorsstabilityai/stable-diffusion-3.5-large | OpenCLIP bigG text encodertext_encoder | Yes | 1.39 GB | Hugging FaceRead 2026-10-24 |
text_encoders/t5xxl_fp16.safetensorsstabilityai/stable-diffusion-3.5-large | T5-XXL text encodertext_encoder | Yes | 9.79 GB | Hugging FaceRead 2026-10-24 |
vae/diffusion_pytorch_model.safetensorsstabilityai/stable-diffusion-3.5-large | VAEvae | Yes | 0.17 GB | Hugging FaceRead 2026-10-24 |
Build sources: SD 3.5 Large GGUF card · ComfyUI-GGUF README.
Q8_0 GGUF
gguf · Q8_0 · 20.37 GB completeMac routes: ComfyUI
| File | Component | Required | Download | Source |
|---|---|---|---|---|
sd3.5_large-Q8_0.ggufcity96/stable-diffusion-3.5-large-gguf | MM-DiT denoiserdit | Yes | 8.78 GB | Hugging FaceRead 2026-10-24 |
text_encoders/clip_l.safetensorsstabilityai/stable-diffusion-3.5-large | CLIP-L text encodertext_encoder | Yes | 0.25 GB | Hugging FaceRead 2026-10-24 |
text_encoders/clip_g.safetensorsstabilityai/stable-diffusion-3.5-large | OpenCLIP bigG text encodertext_encoder | Yes | 1.39 GB | Hugging FaceRead 2026-10-24 |
text_encoders/t5xxl_fp16.safetensorsstabilityai/stable-diffusion-3.5-large | T5-XXL text encodertext_encoder | Yes | 9.79 GB | Hugging FaceRead 2026-10-24 |
vae/diffusion_pytorch_model.safetensorsstabilityai/stable-diffusion-3.5-large | VAEvae | Yes | 0.17 GB | Hugging FaceRead 2026-10-24 |
Build sources: SD 3.5 Large GGUF card · ComfyUI-GGUF README.
Does it fit your Mac's RAM?
Published names the exact measured machine. est. is a memory calculation. unknown means the run verdict is not established, not that the model fails.
| Mac RAM | Complete build | Download | Run verdict | Basis |
|---|---|---|---|---|
| 8 GB | Q4_0 GGUFQ4_0 · ComfyUI | 16.36 GB | Does not fit | est. |
| 16 GB | Q4_0 GGUFQ4_0 · ComfyUI | 16.36 GB | Does not fit | est. |
| 24 GB | Q4_0 GGUFQ4_0 · ComfyUI | 16.36 GB | unknown | unknown |
| 32 GB | Q4_0 GGUFQ4_0 · ComfyUI | 16.36 GB | unknown | unknown |
| 48 GB | Q4_0 GGUFQ4_0 · ComfyUI | 16.36 GB | unknown | unknown |
| 64 GB | Q4_0 GGUFQ4_0 · ComfyUI | 16.36 GB | unknown | unknown |
| 96 GB | Q4_0 GGUFQ4_0 · ComfyUI | 16.36 GB | unknown | unknown |
| 128 GB | Q4_0 GGUFQ4_0 · ComfyUI | 16.36 GB | unknown | unknown |
How does it rank in blind votes?
#81 of 82 in text to image blind votes, from 23,396 votes.
Quality: blind human votes from stable-diffusion-v35-large (arena.ai), CC BY 4.0, snapshot 2026-10-07. Scores are for the Arena checkpoint, not your local quantized build.
Which Mac software routes are listed?
ComfyUI
OfficialFormats: safetensors, gguf. Memory policy: component stages stay resident.
On Apple Silicon ComfyUI runs on PyTorch MPS, not MLX. GGUF files need the separate city96/ComfyUI-GGUF custom node. Resident size is the sum of the weights, an upper bound: ComfyUI can unload models between stages and publishes no per-model Mac peak.
Sources: ComfyUI README · ComfyUI system requirements · ComfyUI CLI arguments · ComfyUI-GGUF README
What does the official configuration say?
"The launch page says the model suits professional use at 1 megapixel resolution. It gives no Large-specific RAM or VRAM minimum."
Source: Stable Diffusion 3.5 announcement · Read 2026-10-24.
What known issues should you check?
Known issue 1
One reported ComfyUI run of SD 3.5 Large on a 16 GB Mac mini M4 failed with an MPS memory error. This is one issue report, not a general 16 GB verdict.
Source: ComfyUI issue 7171 · Read 2026-10-24
Sources
Read 2026-10-24
Read 2026-10-24
Read 2026-10-24
Read 2026-10-24
Read 2026-10-24
Read 2026-10-24
Read 2026-10-24
Read 2026-10-24
Read 2026-10-24