Stable Diffusion 3.5 Large on 8 GB of VRAM
Not at full quality. The 16-bit and 8-bit files are too big for 8 GB; the largest that fits is Q4_1 (5.3 GB). Stability AI's 8B model. City96 only publishes the older GGUF types for it (Q8_0, Q5, Q4), not K-quants.
Runs
Yes, with a compressed file.
Q4_1 (5.3 GB) fits with only 0.4 GB to spare (about 7.6 GB of 8 GB). Quality: good; some loss in fine detail and text. For better quality, Q5_1 (6.3 GB) also runs, with about 0.6 GB spilling into system RAM - a little slower, still practical.
Best fileQ4_1
File size5.3 GB
VRAM needed~7.6 GB
System RAM32 GB+
Memory map · 8 GB GPU7.6 GB / 8 GB
04 GB8 GB
Weights Q4_1 · 5.3 GBWorking memory · 1.5 GBReserve · 0.8 GBFree · 0.4 GB
calculated How this is counted.
01What to download
| Part | File | Folder | Size | |
|---|---|---|---|---|
| Model | sd3.5_large-Q4_1.gguf Q4_1 · city96/stable-diffusion-3.5-large-gguf | models/unet | 5.3 GB | Download → |
| Text encoder | t5xxl_fp8_e4m3fn.safetensors T5-XXL FP8 · Comfy-Org/stable-diffusion-3.5-fp8 | models/text_encoders | 4.9 GB | Download → |
| Text encoder | clip_l.safetensors CLIP-L · Comfy-Org/stable-diffusion-3.5-fp8 | models/text_encoders | 0.2 GB | Download → |
| Text encoder | clip_g.safetensors CLIP-G · Comfy-Org/stable-diffusion-3.5-fp8 | models/text_encoders | 1.4 GB | Download → |
| VAE | diffusion_pytorch_model.safetensors SD 3.5 VAE (gated repo: log in and accept the licence first) · stabilityai/stable-diffusion-3.5-large | models/vae | 0.2 GB | Download → |
| Total download · keep about the same free on disk | 12.0 GB | |||
Alternatives: T5-XXL FP16 (9.8 GB). Sizes from Hugging Face, 2026-10-01.
02Every file, on 8 GB
| File | Size | Needed | On this card | Quality | Download |
|---|---|---|---|---|---|
| 16-bit SAFETENSORS · stabilityai | 16.5 GB | 18.8 GB | 10.8 GB too big | the original weights | Hugging Face → |
| Q8_0 GGUF · city96 | 8.8 GB | 11.1 GB | 3.1 GB too big | practically identical to the original | Hugging Face → |
| Q5_1 GGUF · city96 | 6.3 GB | 8.6 GB | spills 0.6 GB | close; small differences in fine detail | Hugging Face → |
| Q4_1 ← GGUF · city96 | 5.3 GB | 7.6 GB | fits · 0.4 GB spare | good; some loss in fine detail and text | Hugging Face → |
“Needed” adds 1.5 GB of working memory for SD 3.5 Large and a 0.8 GB reserve. Sizes 2026-10-01.